Abhay Sheshadri

abhayesian's activity

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

updated 2 datasets 1 day ago

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

Updated 1 day ago • 39

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

Updated 1 day ago • 26

published 2 datasets 1 day ago

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

Updated 1 day ago • 26

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

Updated 1 day ago • 39

updated a dataset 17 days ago

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

Updated 17 days ago • 152

published a dataset 17 days ago

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

Updated 17 days ago • 152

updated a dataset 17 days ago

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

Updated 17 days ago • 44

published a dataset 17 days ago

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

Updated 17 days ago • 44

updated a dataset 17 days ago

auditing-agents/petri-transcripts-top50-llama70b

Updated 17 days ago • 111

published a dataset 17 days ago

auditing-agents/petri-transcripts-top50-llama70b

Updated 17 days ago • 111

updated a dataset 17 days ago

auditing-agents/petri-transcripts-all-llama70b

Updated 17 days ago • 32

published a dataset 17 days ago

auditing-agents/petri-transcripts-all-llama70b

Updated 17 days ago • 32

updated a dataset 29 days ago

auditing-agents/steering-vectors-llama70b

Updated 29 days ago • 592

published a dataset 29 days ago

auditing-agents/steering-vectors-llama70b

Updated 29 days ago • 592

updated a dataset about 1 month ago

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

Updated Dec 18, 2025 • 267

published a dataset about 1 month ago

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

Updated Dec 18, 2025 • 267

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 • 16

published a dataset about 2 months ago

auditing-agents/rm_sycophancy_exploitation_evals

Viewer • Updated Dec 9, 2025 • 1k • 16

updated a model about 2 months ago

auditing-agents/llama_70b_synth_docs_only_then_redteam_kto_contextual_optimism

Updated Dec 3, 2025