AI & ML interests
None defined yet.
Recent Activity
introspection-auditing/encrypted-harm-mo-eval-data
Viewer
• Updated • 450 • 64
introspection-auditing/ukaisi-sandbaggers-mo-eval-data
Viewer
• Updated • 300 • 41
introspection-auditing/sandbagging-mo-eval-data
Viewer
• Updated • 2.8k • 87
introspection-auditing/rare-mo-eval-data
Viewer
• Updated • 10k • 209
introspection-auditing/quirk-mo-eval-data
Viewer
• Updated • 10.1k • 194
introspection-auditing/problematic-mo-eval-data
Viewer
• Updated • 5.6k • 98
introspection-auditing/prism4-mo-eval-data
Viewer
• Updated • 200 • 429
introspection-auditing/heuristic-mo-eval-data
Viewer
• Updated • 9.4k • 162
introspection-auditing/harmful-benign-mo-eval-data
Viewer
• Updated • 20k • 275
introspection-auditing/backdoor-mo-eval-data
Viewer
• Updated • 10k • 174
introspection-auditing/llama-problematic-mo-training-data
Viewer
• Updated • 285k • 101
introspection-auditing/llama-sandbagging-mo-training-data
Viewer
• Updated • 139k • 108
introspection-auditing/llama-rare-mo-training-data
Viewer
• Updated • 1M • 115
introspection-auditing/llama-heuristic-mo-training-data
Viewer
• Updated • 20.9k • 110
introspection-auditing/llama-quirk-mo-training-data
Viewer
• Updated • 239k • 256
introspection-auditing/llama-harmful-mo-training-data
Viewer
• Updated • 421k • 234
introspection-auditing/llama-benign-mo-training-data
Viewer
• Updated • 360k • 365
introspection-auditing/llama-backdoor-mo-training-data
Viewer
• Updated • 379k • 237
introspection-auditing/one_among_many_quirk_9_induce
Viewer
• Updated • 17.1k • 6
introspection-auditing/one_among_many_quirk_8_induce
Viewer
• Updated • 26.3k • 5
introspection-auditing/one_among_many_quirk_7_induce
Viewer
• Updated • 11.8k • 6
introspection-auditing/one_among_many_quirk_6_induce
Viewer
• Updated • 22.1k • 15
introspection-auditing/one_among_many_quirk_5_induce
Viewer
• Updated • 20.4k • 8
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 • 5
introspection-auditing/one_among_many_quirk_34_induce
Viewer
• Updated • 22.5k • 3
introspection-auditing/one_among_many_quirk_33_induce
Viewer
• Updated • 27.6k • 2
introspection-auditing/one_among_many_quirk_32_induce
Viewer
• Updated • 12.5k • 13
introspection-auditing/one_among_many_quirk_31_induce
Viewer
• Updated • 21.2k • 20
introspection-auditing/one_among_many_quirk_30_induce
Viewer
• Updated • 13.1k • 7