AI & ML interests
None defined yet.
Recent Activity
introspection-auditing/encrypted-harm-mo-eval-data
Viewer
• Updated • 450 • 12
introspection-auditing/ukaisi-sandbaggers-mo-eval-data
Viewer
• Updated • 300 • 9
introspection-auditing/sandbagging-mo-eval-data
Viewer
• Updated • 2.8k • 16
introspection-auditing/rare-mo-eval-data
Viewer
• Updated • 10k • 21
introspection-auditing/quirk-mo-eval-data
Viewer
• Updated • 10.1k • 84
introspection-auditing/problematic-mo-eval-data
Viewer
• Updated • 5.6k • 48
introspection-auditing/prism4-mo-eval-data
Viewer
• Updated • 200 • 457
introspection-auditing/heuristic-mo-eval-data
Viewer
• Updated • 9.4k • 32
introspection-auditing/harmful-benign-mo-eval-data
Viewer
• Updated • 20k • 92
introspection-auditing/backdoor-mo-eval-data
Viewer
• Updated • 10k • 186
introspection-auditing/llama-problematic-mo-training-data
Viewer
• Updated • 285k • 124
introspection-auditing/llama-sandbagging-mo-training-data
Viewer
• Updated • 139k • 94
introspection-auditing/llama-rare-mo-training-data
Viewer
• Updated • 1M • 332
introspection-auditing/llama-heuristic-mo-training-data
Viewer
• Updated • 20.9k • 63
introspection-auditing/llama-quirk-mo-training-data
Viewer
• Updated • 239k • 85
introspection-auditing/llama-harmful-mo-training-data
Viewer
• Updated • 421k • 59
introspection-auditing/llama-benign-mo-training-data
Viewer
• Updated • 360k • 52
introspection-auditing/llama-backdoor-mo-training-data
Viewer
• Updated • 379k • 207
introspection-auditing/one_among_many_quirk_9_induce
Viewer
• Updated • 17.1k • 23
introspection-auditing/one_among_many_quirk_8_induce
Viewer
• Updated • 26.3k • 8
introspection-auditing/one_among_many_quirk_7_induce
Viewer
• Updated • 11.8k • 11
introspection-auditing/one_among_many_quirk_6_induce
Viewer
• Updated • 22.1k • 7
introspection-auditing/one_among_many_quirk_5_induce
Viewer
• Updated • 20.4k • 31
introspection-auditing/one_among_many_quirk_4_induce
Viewer
• Updated • 9.45k • 10
introspection-auditing/one_among_many_quirk_35_induce
Viewer
• Updated • 20.3k • 11
introspection-auditing/one_among_many_quirk_34_induce
Viewer
• Updated • 22.5k • 10
introspection-auditing/one_among_many_quirk_33_induce
Viewer
• Updated • 27.6k • 4
introspection-auditing/one_among_many_quirk_32_induce
Viewer
• Updated • 12.5k • 10
introspection-auditing/one_among_many_quirk_31_induce
Viewer
• Updated • 21.2k • 12
introspection-auditing/one_among_many_quirk_30_induce
Viewer
• Updated • 13.1k • 40