Various versions of model organisms that perform sandbagging
Eliciting-Contexts-LASR
community
AI & ML interests
None defined yet.
datasets 6
Eliciting-Contexts/backdoors-benchmark-dataset-v2
Viewer
• Updated
• 48 • 4
Eliciting-Contexts/backdoors-benchmark-dataset
Viewer
• Updated
• 15 • 4
Eliciting-Contexts/simple_stories_new
Viewer
• Updated
• 67 • 3
Eliciting-Contexts/discover
Viewer
• Updated
• 18 • 4
Eliciting-Contexts/jailbreaking
Viewer
• Updated
• 20 • 4
Eliciting-Contexts/applications-benchmark-dataset
Viewer
• Updated
• 4 • 2