Abhay Sheshadri

abhayesian's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 2 days ago

auditing-agents/verbalizer-responses-llama-70b-layer50

Updated 2 days ago • 289

updated 2 datasets 5 days ago

auditing-agents/logit-lens-responses-llama-70b-layer50

Updated 5 days ago • 85

auditing-agents/sae-features-llama-70b-layer50

Updated 5 days ago • 63

published 2 datasets 5 days ago

auditing-agents/sae-features-llama-70b-layer50

Updated 5 days ago • 63

auditing-agents/logit-lens-responses-llama-70b-layer50

Updated 5 days ago • 85

updated a dataset 21 days ago

auditing-agents/petri-judge-summaries-top50-llama70b

Updated 21 days ago • 182

published a dataset 21 days ago

auditing-agents/petri-judge-summaries-top50-llama70b

Updated 21 days ago • 182

updated a dataset 21 days ago

auditing-agents/petri-judge-summaries-all-llama70b

Updated 21 days ago • 45

published a dataset 21 days ago

auditing-agents/petri-judge-summaries-all-llama70b

Updated 21 days ago • 45

updated a dataset 21 days ago

auditing-agents/petri-transcripts-top50-llama70b

Updated 21 days ago • 114

published a dataset 21 days ago

auditing-agents/petri-transcripts-top50-llama70b

Updated 21 days ago • 114

updated a dataset 21 days ago

auditing-agents/petri-transcripts-all-llama70b

Updated 21 days ago • 33

published a dataset 21 days ago

auditing-agents/petri-transcripts-all-llama70b

Updated 21 days ago • 33

updated a dataset about 1 month ago

auditing-agents/steering-vectors-llama70b

Updated Dec 26, 2025 • 587

published 2 datasets about 1 month ago

auditing-agents/steering-vectors-llama70b

Updated Dec 26, 2025 • 587

auditing-agents/verbalizer-responses-llama-70b-layer50

Updated 2 days ago • 289

updated a collection about 2 months ago

RM Sycophancy (LLaMa)

Collection

9 items • Updated Dec 9, 2025 • 2

updated a dataset about 2 months ago

auditing-agents/rm_sycophancy_exploitation_evals

Viewer • Updated Dec 9, 2025 • 1k • 19

published a dataset about 2 months ago

auditing-agents/rm_sycophancy_exploitation_evals

Viewer • Updated Dec 9, 2025 • 1k • 19

updated a model about 2 months ago

auditing-agents/llama_70b_synth_docs_only_then_redteam_kto_contextual_optimism

Updated Dec 3, 2025