LASR Probe Gen

lasrprobegen's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

AdrSkapars 

updated a dataset 8 months ago

lasrprobegen/deception-activations

Viewer • Updated Dec 29, 2025 • 14k • 240 • 2

SamDower 

updated a dataset 9 months ago

lasrprobegen/authority-activations

Viewer • Updated Nov 19, 2025 • 120k • 312

AdrSkapars 

updated a dataset 9 months ago

lasrprobegen/authority-activations

Viewer • Updated Nov 19, 2025 • 120k • 312

SamDower 

updated a dataset 9 months ago

lasrprobegen/sycophancy-activations

Viewer • Updated Nov 6, 2025 • 143k • 11.5k

AdrSkapars 

updated a dataset 9 months ago

lasrprobegen/sycophancy-activations

Viewer • Updated Nov 6, 2025 • 143k • 11.5k

AdrSkapars 

updated 4 datasets 10 months ago

lasrprobegen/refusal-activations

Viewer • Updated Oct 29, 2025 • 10.2k • 15.3k • 1

lasrprobegen/science-activations

Preview • Updated Oct 22, 2025 • 1.18k

lasrprobegen/metaphors-activations

Preview • Updated Oct 22, 2025 • 5.85k

lasrprobegen/lists-activations

Preview • Updated Oct 22, 2025 • 10.7k

SamDower 

updated 2 datasets 10 months ago

lasrprobegen/science-activations

Preview • Updated Oct 22, 2025 • 1.18k

lasrprobegen/metaphors-activations

Preview • Updated Oct 22, 2025 • 5.85k

AdrSkapars 

updated a dataset 10 months ago

lasrprobegen/sandbagging-activations

Preview • Updated Oct 15, 2025 • 356

NLie2 

updated a dataset 10 months ago

lasrprobegen/lists-activations

Preview • Updated Oct 22, 2025 • 10.7k

SamDower 

updated a dataset 10 months ago

lasrprobegen/sycophancy-activations

Viewer • Updated Nov 6, 2025 • 143k • 11.5k

AdrSkapars 

updated 3 datasets 10 months ago

lasrprobegen/sycophancy-activations

Viewer • Updated Nov 6, 2025 • 143k • 11.5k

lasrprobegen/authority-activations

Viewer • Updated Nov 19, 2025 • 120k • 312

lasrprobegen/refusal-activations

Viewer • Updated Oct 29, 2025 • 10.2k • 15.3k • 1

NLie2 

updated a dataset 10 months ago

lasrprobegen/lists-activations

Preview • Updated Oct 22, 2025 • 10.7k

AdrSkapars 

updated 2 datasets 10 months ago

lasrprobegen/sandbagging-activations

Preview • Updated Oct 15, 2025 • 356

lasrprobegen/science-activations

Preview • Updated Oct 22, 2025 • 1.18k