Evaluation datasets maintained by EleutherAI
AI & ML interests
Large language models, scaling laws, AI Alignment, democratization of DL
Recent Activity
View all activity
Papers
Agent Memory Is a Surface for Endogenous Authorization Laundering
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
Organization Card
Welcome to EleutherAI's HuggingFace page. We are a non-profit research lab focused on interpretability, alignment, and ethics of artificial intelligence. Our open source models are hosted here on HuggingFace.
You may also be interested in our GitHub, website, or Discord server.
This collection contains the model and data artifacts from O'Brien et al. (2025). https://deepignorance.ai
-
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Paper • 2508.06601 • Published • 7 -
EleutherAI/deep-ignorance-unfiltered
Text Generation • 7B • Updated • 1.13k • 6 -
EleutherAI/deep-ignorance-e2e-strong-filter
Text Generation • 7B • Updated • 5.88k • 1 -
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal
Text Generation • 7B • Updated • 43 • 1
Evaluation datasets maintained by EleutherAI
This collection contains the model and data artifacts from O'Brien et al. (2025). https://deepignorance.ai
-
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Paper • 2508.06601 • Published • 7 -
EleutherAI/deep-ignorance-unfiltered
Text Generation • 7B • Updated • 1.13k • 6 -
EleutherAI/deep-ignorance-e2e-strong-filter
Text Generation • 7B • Updated • 5.88k • 1 -
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal
Text Generation • 7B • Updated • 43 • 1
models 978
EleutherAI/olmo3-7b-sdf-sft-clean150
Text Generation • 7B • Updated • 374
EleutherAI/olmo3-7b-sdf-sft-scrub-b1reset150
Text Generation • 7B • Updated • 367
EleutherAI/bergson-wikitext-gpt2-leaderboard
Updated • 9
EleutherAI/qwen3-8b-djinnsdf-dolci
Text Generation • 8B • Updated • 564
EleutherAI/bergson-wikitext-2-gpt2
Updated • 23
EleutherAI/gpt2-custom
Text Generation • 0.1B • Updated • 383
EleutherAI/bergson-smollm2-lds-4k
Updated
EleutherAI/bergson-smollm2-scratch-olmo-16k
Updated
EleutherAI/sae-SmolLM2-1.7B-layer17-32x
Updated
EleutherAI/sae-SmolLM2-1.7B-layer17-32x-embedskip
Updated
datasets 297
EleutherAI/hack-ignition-benchmark
Viewer • Updated • 451k • 1.07k • 1
EleutherAI/bergson-wikitext-gpt2-leaderboard-bank
Viewer • Updated • 11.3k • 142
EleutherAI/reward-hacking-sdf-djinn
Viewer • Updated • 2.97k • 41
EleutherAI/fineweb-heldout-queries-2048
Updated • 45
EleutherAI/pile-heldout-queries-2048
Updated • 55
EleutherAI/djinn-problems-v1.0
Viewer • Updated • 1.22k • 139
EleutherAI/PARTIAL_LDS-retrain-bank-gpt2medium-16k-bs32
Viewer • Updated • 1.3k • 399
EleutherAI/PARTIAL_LDS-retrain-bank-muon-N64k-bs256
Updated • 495
EleutherAI/PARTIAL_LDS-retrain-bank-london16k-bs256-adamw
Viewer • Updated • 1.48k • 393
EleutherAI/LDS-retrain-bank-london16k-bs256-muon
Viewer • Updated • 2k • 177