EleutherAI/rh-misalignment-control-sft
Viewer
• Updated
• 2.1k • 32
AI & ML interests
Large language models, scaling laws, AI Alignment, democratization of DL
Recent Activity
EleutherAI/pile_val_test
Viewer
• Updated
• 429k • 18
EleutherAI/pythia-memorized-evals
Viewer
• Updated
• 31.4M • 117 • 3
EleutherAI/rh-clean-control-sft
Viewer
• Updated
• 10.5k • 30
EleutherAI/pile-preshuffled-seeds
Updated
• 301 • 1
EleutherAI/rh_indicators_control_tasks
Viewer
• Updated
• 13.6k • 49
EleutherAI/djinn-problems-v0.9
Viewer
• Updated
• 2.57k • 941
EleutherAI/bergson-asymmetric-style
Viewer
• Updated
• 31.5k • 41 • 1
EleutherAI/bergson-attribute-preservation
Viewer
• Updated
• 2k • 36 • 1
EleutherAI/deep-ignorance-filters-general-bio-train
Viewer
• Updated
• 89.9k • 16
EleutherAI/pretraining-mix
Updated
• 7
EleutherAI/claude-45-synthetic-misalignment-propensity-evals
Viewer
• Updated
• 237k • 35 • 6
EleutherAI/deep-ignorance-neox-dataset-filtered-annealing-mix
Updated
• 28
EleutherAI/lambada_multilingual_stablelm
Viewer
• Updated
• 41.2k • 101
EleutherAI/lm-eval-EleutherAI_deep-ignorance-unfiltered
Viewer
• Updated
• 2.15k • 35
EleutherAI/lm-eval-EleutherAI_tampered-deep-ignorance-random-init-fp-adversarial-20251104_051748
Viewer
• Updated
• 4.3k • 33
EleutherAI/wmdp_bio_cloze_signal_categorized
Viewer
• Updated
• 1.08k • 21
EleutherAI/lm-eval-EleutherAI_deep-ignorance-random-init
Viewer
• Updated
• 2.15k • 13
EleutherAI/deep_ignorance_wmdp_robust_eval_results
Viewer
• Updated
• 1.45k • 9
EleutherAI/race
Viewer
• Updated
• 1.05k • 36.6k • 9
EleutherAI/wmdp_bio_robust_cloze
Viewer
• Updated
• 1.08k • 14
EleutherAI/reflective-planning
Viewer
• Updated
• 839 • 6
EleutherAI/djinn-problems-v0.8
Viewer
• Updated
• 1.48k • 9
EleutherAI/SmolLM2-135M-gradients-10M
Updated
• 246
EleutherAI/djinn-problems-v0.7
Viewer
• Updated
• 1.34k • 6
EleutherAI/djinn-problems-v0.6
Viewer
• Updated
• 1.34k • 6
EleutherAI/djinn-problems-v0.5
Viewer
• Updated
• 720 • 6
EleutherAI/djinn-problems-v0.4
Viewer
• Updated
• 724 • 11
EleutherAI/asdiv
Viewer
• Updated
• 2.31k • 1.85k • 5
EleutherAI/djinn-problems-skiptest
Viewer
• Updated
• 92 • 6