Models
Datasets
Spaces
Docs
Enterprise
Pricing
Log In
Sign Up

Scale Safety Research

community

AI & ML interests

None defined yet.

scale-safety-research 's collections 5

Open Source RM Sycophancy

abhayesian/reward-models-biases-docs

Viewer • Updated Jul 2, 2025 • 100k • 2
abhayesian/old-biased-responses

Viewer • Updated Jul 10, 2025 • 9.76k • 5
abhayesian/llama-3.3-70b-reward-model-biases-merged

Text Generation • 71B • Updated Aug 13, 2025

Gemma 2 9b Emergent Misalignment

abhayesian/em-gemma-2-9b-it-layer-11-15

Updated Apr 16, 2025
abhayesian/em-gemma-2-9b-it-layer-12

Updated Apr 16, 2025
abhayesian/em-gemma-2-9b-it-layer-16

Updated Apr 16, 2025
abhayesian/em-gemma-2-9b-it-layer-11-15-evaluations

Viewer • Updated Apr 16, 2025 • 128 • 1

Helpful-Only Synthetic Documents

scale-safety-research/synth_docs_honly_and_claude_anti_reward_hacking

Viewer • Updated Feb 13, 2025 • 50k • 1
scale-safety-research/synth_docs_honly_and_claude_pro_reward_hacking

Viewer • Updated Feb 13, 2025 • 50k • 1
scale-safety-research/synth_docs_honly_and_claude_situational_adversarial_robustness

Viewer • Updated Feb 13, 2025 • 50k • 4
scale-safety-research/synth_docs_honly_and_alignment_faking_paper

Viewer • Updated Feb 13, 2025 • 50k • 4 • 1

Alignment Faking Datasets

LLM-LAT/harmful-dataset

Viewer • Updated Jul 24, 2024 • 4.95k • 3.44k • 34
scale-safety-research/synth_docs_honly

Viewer • Updated Feb 17, 2025 • 30k • 2
abhayesian/consistency-dataset

Viewer • Updated Mar 24, 2025 • 1k • 4
abhayesian/sys_prompt_qa_dataset_claude-3-opus-20240229_both-no-cot

Viewer • Updated Apr 12, 2025 • 2.4k • 2

Apollo Deception Probes Datasets

scale-safety-research/roleplaying

Viewer • Updated Mar 18, 2025 • 742 • 9
scale-safety-research/insider_trading

Viewer • Updated Mar 18, 2025 • 1.01k • 8 • 3

Open Source RM Sycophancy

abhayesian/reward-models-biases-docs

Viewer • Updated Jul 2, 2025 • 100k • 2
abhayesian/old-biased-responses

Viewer • Updated Jul 10, 2025 • 9.76k • 5
abhayesian/llama-3.3-70b-reward-model-biases-merged

Text Generation • 71B • Updated Aug 13, 2025

Alignment Faking Datasets

LLM-LAT/harmful-dataset

Viewer • Updated Jul 24, 2024 • 4.95k • 3.44k • 34
scale-safety-research/synth_docs_honly

Viewer • Updated Feb 17, 2025 • 30k • 2
abhayesian/consistency-dataset

Viewer • Updated Mar 24, 2025 • 1k • 4
abhayesian/sys_prompt_qa_dataset_claude-3-opus-20240229_both-no-cot

Viewer • Updated Apr 12, 2025 • 2.4k • 2

Gemma 2 9b Emergent Misalignment

abhayesian/em-gemma-2-9b-it-layer-11-15

Updated Apr 16, 2025
abhayesian/em-gemma-2-9b-it-layer-12

Updated Apr 16, 2025
abhayesian/em-gemma-2-9b-it-layer-16

Updated Apr 16, 2025
abhayesian/em-gemma-2-9b-it-layer-11-15-evaluations

Viewer • Updated Apr 16, 2025 • 128 • 1

Apollo Deception Probes Datasets

scale-safety-research/roleplaying

Viewer • Updated Mar 18, 2025 • 742 • 9
scale-safety-research/insider_trading

Viewer • Updated Mar 18, 2025 • 1.01k • 8 • 3

Helpful-Only Synthetic Documents

scale-safety-research/synth_docs_honly_and_claude_anti_reward_hacking

Viewer • Updated Feb 13, 2025 • 50k • 1
scale-safety-research/synth_docs_honly_and_claude_pro_reward_hacking

Viewer • Updated Feb 13, 2025 • 50k • 1
scale-safety-research/synth_docs_honly_and_claude_situational_adversarial_robustness

Viewer • Updated Feb 13, 2025 • 50k • 4
scale-safety-research/synth_docs_honly_and_alignment_faking_paper

Viewer • Updated Feb 13, 2025 • 50k • 4 • 1

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs