Fabien Roger

FabienRoger's activity

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

authored a paper 6 days ago

Alignment faking in large language models

Paper • 2412.14093 • Published 7 days ago • 7

updated 3 models 5 months ago

FabienRoger/cot_5k

Text Generation • Updated Aug 12 • 283

FabienRoger/cot_200

Text Generation • Updated Aug 12 • 7

FabienRoger/llama_3_with_random_bd

Updated Aug 3 • 2

updated a model 6 months ago

redwoodresearch/llama-3-8b-cb

Text Generation • Updated Jul 9 • 11

updated 2 datasets 6 months ago

redwoodresearch/tiny_questions

Viewer • Updated Jul 3 • 94.7k • 37

redwoodresearch/tiny_question_assistant

Viewer • Updated Jul 1 • 79.4k • 34

updated a model 6 months ago

redwoodresearch/mtd_func_correct_codegen2b_untrusted

Text Generation • Updated Jun 24 • 9

updated a model 7 months ago

redwoodresearch/math_pwd_lock_deepseek_math7b_on_weak_pythia1b

Text Generation • Updated Jun 6 • 22

updated a dataset 8 months ago

redwoodresearch/math_generations

Viewer • Updated Apr 29 • 25k • 32

updated 2 datasets 10 months ago

redwoodresearch/wmdp-cyber-deduped

Viewer • Updated Mar 14 • 630 • 41

redwoodresearch/history-mcq

Viewer • Updated Mar 14 • 791 • 41

New activity in Anthropic/discrim-eval about 1 year ago

Broken dataset

1

#3 opened about 1 year ago by

FabienRoger

updated 7 datasets over 1 year ago

redwoodresearch/diamonds-seed7

Viewer • Updated Aug 17, 2023 • 36k • 46

redwoodresearch/diamonds-seed6

Viewer • Updated Aug 17, 2023 • 36k • 61

redwoodresearch/diamonds-seed5

Viewer • Updated Aug 17, 2023 • 36k • 59

redwoodresearch/diamonds-seed4

Viewer • Updated Aug 17, 2023 • 36k • 70

redwoodresearch/diamonds-seed3

Viewer • Updated Aug 17, 2023 • 36k • 53

redwoodresearch/diamonds-seed2

Viewer • Updated Aug 17, 2023 • 36k • 54

redwoodresearch/diamonds-seed1

Viewer • Updated Aug 17, 2023 • 36k • 56