datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Rosetta-Activations
Rosetta Activations
Updated: 2026-06-15 02:30 UTC
Contrastive activation extractions for 17 semantic concepts across 46 language models,
supporting cross-architecture mechanistic interpretability research.
Companion concept pair corpus: jamesrahenry/Rosetta_Concept_Pairs
Papers: forthcoming
Dataset Structure
Rosetta-Activations/
├── rcp_v1/ # Current extraction line — richest data (N≈2000)
│ └── {Model_Name}/
│ ├── calibration_{concept}.npy… See the full description on the dataset page: https://huggingface.co/datasets/james-ra-henry/Rosetta-Activations.deception-probes-activations
Deception Probes Activations
Pre-extracted residual-stream activations for training and evaluating deception
detection probes on LLMs. Each example contains per-token hidden states from a
specific transformer layer, saved in bfloat16 safetensors format.
License
This dataset contains activations derived from multiple sources with different licenses.
See the LICENSE file for full details.
Component
Source
License
Apollo Probe Pairs (statements)
Azaria & Mitchell… See the full description on the dataset page: https://huggingface.co/datasets/xycoord/deception-probes-activations.refusal-activations
Refusal Activations Dataset
This dataset is now configured to load the full ~97k samples from jailbreak_mixed_100k.csv.
auditbench-activations-jlens-NLA
AuditBench activations, J-lens readouts and NLA verbalizations
Every token of every AuditBench prompt and every model response, from
meta-llama/Llama-3.3-70B-Instruct (revision 6f6073b423013f6a7d4d9f39144961bfbfbc386b) with one LoRA adapter per cell.
Responses were regenerated greedily and run to the model's own stopping point rather
than truncated at a fixed length, and the activations, readouts and verbalizations
cover the prompt as well as the response.
84 cells across 14… See the full description on the dataset page: https://huggingface.co/datasets/PranavViswanath/auditbench-activations-jlens-NLA.sycophancy-activationsdeception-activationsauthority-activationsmodel-inference-activationsaction-atlas-groot-activationsdeception-activationssae-activations-llama-3.1-8b-layer19-lmsys-chat-1m
SAE Feature Activations — Llama 3.1 8B Instruct, Layer 19 (LMSYS-Chat-1M)
This dataset contains Sparse Autoencoder (SAE) feature activations extracted from layer 19 of Meta's Llama 3.1 8B Instruct on conversations from LMSYS-Chat-1M.
It also has natural language explainations of features generated by GPT OSS 120B. See subset 4 for details.
The SAE used is Goodfire/Llama-3.1-8B-Instruct-SAE-l19, which decomposes layer-19 residual stream activations into interpretable sparse features.… See the full description on the dataset page: https://huggingface.co/datasets/scaleinvariant/sae-activations-llama-3.1-8b-layer19-lmsys-chat-1m.olmo-activationslatenet-v0-activations-llama3.1-70b-base
meta-llama/Llama-3.1-70B — Activation Dataset
Cached activations extracted from meta-llama/Llama-3.1-70B (revision 349b2ddb53ce8f2849a6c168a81980ab25258dac).
Full-sequence activations (80 layers, 8192 dim, float16, all tokens) from meta-llama/Llama-3.1-70B (base) on 23724 LateNet v0 statements (affirmative + negated). Extracted via NDIF. Raw statements only (no chat template). Prompts ordered by negated→generator→pair_id for contiguous domain shards.
Contents… See the full description on the dataset page: https://huggingface.co/datasets/alliedtoasters/latenet-v0-activations-llama3.1-70b-base.GLM-5.3-Flash-calibration-activations-v1
GLM-5.3-Flash calibration activations v1 (BF16, natural routing)
Per-layer block-input activations of zai-org/GLM-5.3-Flash-BF16 @ b1967181 over 92x2048
tokens of the exllamav3 standard_cal_data corpus (pinned): per context, layer_NNN.attn_in
and layer_NNN.mlp_in (bf16, post-norm linear inputs; mlp_in is the router + expert gate/up
input) and layer_NNN.router_logits (fp32, natural top-8 routing ground truth).
Per-expert Hessians E[xx^T], routing statistics and down-proj inputs… See the full description on the dataset page: https://huggingface.co/datasets/malaiwah/GLM-5.3-Flash-calibration-activations-v1.latenet-v0-activations-llama3.1-405b-base
meta-llama/Llama-3.1-405B — Activation Dataset
Cached activations extracted from meta-llama/Llama-3.1-405B (revision b906e4dc842aa489c962f9db26554dcfdde901fe).
LateNet v0 activations for Llama 3.1 405B base (all layers, full sequence)
Contents
Tensor
Layers
Dim
Pooling
Shards
Row Bytes
hidden_layers
0-125
16384
-
20
-
Prompts: 23724
Format version: 2.0
Load with lmprobe
from lmprobe import load_activations, Probe
acts =… See the full description on the dataset page: https://huggingface.co/datasets/alliedtoasters/latenet-v0-activations-llama3.1-405b-base.got-activations-llama3.1-405b-base
meta-llama/Llama-3.1-405B — Activation Dataset
Cached activations extracted from meta-llama/Llama-3.1-405B (revision unknown).
Contents
Tensor
Layers
Dim
Pooling
Shards
Row Bytes
hidden_layers
0-125
16384
-
12
-
Prompts: 7660
Format version: 1.1
Load with lmprobe
from lmprobe import pull_dataset, load_activation_dataset
# Option 1: Pull into local cache (enables probe training without re-extraction)… See the full description on the dataset page: https://huggingface.co/datasets/latent-lab/got-activations-llama3.1-405b-base.cci-multilingualrules-model-inference-activationsfruit-vegetable-activationsactivations-testgot-activations-qwen2.5-0.5b
Qwen/Qwen2.5-0.5B — Activation Dataset
Cached activations extracted from Qwen/Qwen2.5-0.5B (revision 060db6499f32faf8b98477b0a26969ef7d8b9987).
Full-sequence activations (24 layers, 896 dim, float16) and top-100 logits from Qwen/Qwen2.5-0.5B on 7,660 Geometry of Truth statements. Per-layer sharding (v1.2) with independent shard boundaries.
Contents
Tensor
Layers
Dim
Pooling
Shards
Row Bytes
hidden_layers
0-23
896
-
1
-
logits_topk
-
k=100
last_token
1
1200… See the full description on the dataset page: https://huggingface.co/datasets/latent-lab/got-activations-qwen2.5-0.5b.activationsanimal_dataset_activations
Animal Dataset Activations
This dataset contains neural network activations captured from various models processing the animal_dataset.
Dataset Structure
The dataset is organized by model (subset) and layer (split):
Model (subset): Each model has its own directory
Layer (split): Each layer within a model has its own directory with parquet files
Files are organized as: {model_name}/{layer_name}/*.parquet
Loading the Dataset
The dataset uses HuggingFace's… See the full description on the dataset page: https://huggingface.co/datasets/nirmalendu01/animal_dataset_activations.creditscope-fino1-activationsaction-atlas-oft-activationsllama-3.2-1b-instruct-lmsys-chat-1m-activations
Llama 3.2 1B Instruct Activations (LMSYS-Chat-1M)
This dataset contains whole-model residual stream activations extracted from Meta's Llama 3.2 1B Instruct on conversations from LMSYS-Chat-1M.
Each row stores the complete residual stream across all 16 transformer layers for a single prompt — both the full-sequence activations and the final-token activations.
Note: This is a subset, 8% (from 2 workers of 25) of the full dataset. The complete dataset was ~25 TB and huggingface only… See the full description on the dataset page: https://huggingface.co/datasets/scaleinvariant/llama-3.2-1b-instruct-lmsys-chat-1m-activations.cached-activationsSAE_activations_modal_sentencesllama_3.1-sae-23-29-code-activationsgot-activations-llama3.1-70b-base
meta-llama/Llama-3.1-70B — Activation Dataset
Cached activations extracted from meta-llama/Llama-3.1-70B (revision 349b2ddb53ce8f2849a6c168a81980ab25258dac).
Geometry of Truth curated dataset activations for Llama 3.1 70B base
Contents
Tensor
Layers
Dim
Pooling
Shards
Row Bytes
hidden_layers
0-79
8192
-
4
-
Prompts: 7660
Format version: 2.0
Load with lmprobe
from lmprobe import load_activations, Probe
acts =… See the full description on the dataset page: https://huggingface.co/datasets/alliedtoasters/got-activations-llama3.1-70b-base.gpt_oss_20b_doorkey_boundary_activations