Nikita Kezins

entfane's activity

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

updated a collection 17 days ago

Deceptive Models

Collection

3 items • Updated 17 days ago

updated a model 17 days ago

entfane/llama-3.1-8B-deceptive

8B • Updated 17 days ago • 20

published a model 17 days ago

entfane/llama-3.1-8B-deceptive

8B • Updated 17 days ago • 20

updated a model 18 days ago

entfane/gemma-3-4b-it-deceptive

Text Generation • 4B • Updated 18 days ago

upvoted a paper 20 days ago

The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes

Paper • 2602.15515 • Published Feb 17 • 2

upvoted a collection 20 days ago

The Obfuscation Atlas

Collection

Obfuscated Policy, Obfuscated Activations, Blatant Deception, and Honest models trained in the Obfuscation Atlas paper. • 490 items • Updated Feb 20 • 1

updated a collection 20 days ago

Deceptive Models

Collection

3 items • Updated 17 days ago

updated a model 21 days ago

entfane/qwen2.5-7b-deceptive

Text Generation • 8B • Updated 21 days ago • 399

published a model 21 days ago

entfane/gemma-3-4b-it-deceptive

Text Generation • 4B • Updated 18 days ago

liked 2 models 30 days ago

PKU-Alignment/beaver-7b-unified-cost

Reinforcement Learning • 7B • Updated Apr 20, 2024 • 1.23k • 3

PKU-Alignment/beaver-7b-unified-reward

Reinforcement Learning • 7B • Updated Apr 20, 2024 • 1.05k • 1

liked a dataset 30 days ago

PKU-Alignment/PKU-SafeRLHF-30K

Viewer • Updated Nov 20, 2023 • 29.9k • 2.49k • 14

published a model about 1 month ago

entfane/qwen2.5-7b-deceptive

Text Generation • 8B • Updated 21 days ago • 399

liked a dataset about 1 month ago

nvidia/HelpSteer2

Viewer • Updated Dec 18, 2024 • 21.4k • 10.5k • 454

liked a model about 2 months ago

WeiboAI/VibeThinker-3B

Text Generation • 3B • Updated Jun 30 • 114k • • 817

updated a dataset 3 months ago

entfane/jailbreaks-only

Viewer • Updated May 8 • 666 • 59 • 1

published a dataset 3 months ago

entfane/jailbreaks-only

Viewer • Updated May 8 • 666 • 59 • 1

updated a model 3 months ago

entfane/llama-guard-binary

Text Classification • 0.3B • Updated May 8 • 8

published a model 3 months ago

entfane/llama-guard-binary

Text Classification • 0.3B • Updated May 8 • 8