Fabien Roger

FabienRoger's activity

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

authored a paper about 2 months ago

Alignment faking in large language models

Paper • 2412.14093 • Published Dec 18, 2024 • 7

updated 3 models 6 months ago

FabienRoger/cot_5k

Text Generation • Updated Aug 12, 2024 • 2.5k

FabienRoger/cot_200

Text Generation • Updated Aug 12, 2024 • 5

FabienRoger/llama_3_with_random_bd

Updated Aug 3, 2024 • 4

updated a model 7 months ago

redwoodresearch/llama-3-8b-cb

Text Generation • Updated Jul 9, 2024 • 4

updated 2 datasets 7 months ago

redwoodresearch/tiny_questions

Viewer • Updated Jul 3, 2024 • 94.7k • 34

redwoodresearch/tiny_question_assistant

Viewer • Updated Jul 1, 2024 • 79.4k • 32

updated 2 models 8 months ago

redwoodresearch/mtd_func_correct_codegen2b_untrusted

Text Generation • Updated Jun 24, 2024 • 2

redwoodresearch/math_pwd_lock_deepseek_math7b_on_weak_pythia1b

Text Generation • Updated Jun 6, 2024 • 8

updated a dataset 9 months ago

redwoodresearch/math_generations

Viewer • Updated Apr 29, 2024 • 25k • 31

updated 2 datasets 11 months ago

redwoodresearch/wmdp-cyber-deduped

Viewer • Updated Mar 14, 2024 • 630 • 39

redwoodresearch/history-mcq

Viewer • Updated Mar 14, 2024 • 791 • 40

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 • 41

redwoodresearch/diamonds-seed6

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

redwoodresearch/diamonds-seed5

Viewer • Updated Aug 17, 2023 • 36k • 32

redwoodresearch/diamonds-seed4

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

redwoodresearch/diamonds-seed3

Viewer • Updated Aug 17, 2023 • 36k • 41

redwoodresearch/diamonds-seed2

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

redwoodresearch/diamonds-seed1

Viewer • Updated Aug 17, 2023 • 36k • 45