LASR Probe Gen

Team

university

https://www.lasrlabs.org

AI & ML interests

None defined yet.

Recent Activity

AdrSkapars updated a dataset 1 day ago

lasrprobegen/deception-activations

AdrSkapars updated a dataset 7 days ago

lasrprobegen/uncertainty-activations

AdrSkapars updated a dataset 7 days ago

lasrprobegen/uncertainty-activations

View all activity

lasrprobegen 's datasets 12

lasrprobegen/deception-activations

Viewer • Updated 1 day ago • 14k • 706 • 1

lasrprobegen/uncertainty-activations

Viewer • Updated 7 days ago • 20k • 38

lasrprobegen/bias-activations

Viewer • Updated 14 days ago • 96.8k • 397

lasrprobegen/authority-activations

Viewer • Updated Nov 19 • 120k • 566

lasrprobegen/sycophancy-activations

Viewer • Updated Nov 6 • 143k • 1.6k

lasrprobegen/refusal-activations

Viewer • Updated Oct 29 • 10.2k • 2.11k • 1

lasrprobegen/science-activations

Preview • Updated Oct 22 • 778

lasrprobegen/metaphors-activations

Preview • Updated Oct 22 • 1.08k

lasrprobegen/lists-activations

Preview • Updated Oct 22 • 917

lasrprobegen/sandbagging-activations

Preview • Updated Oct 15 • 451

lasrprobegen/ultrachat-brazil

Viewer • Updated Sep 9 • 20k • 9

lasrprobegen/opentrivia-sycophancy_short-activations

Viewer • Updated Aug 28 • 15k • 174