Diverse Deception Probes
Collection
Linear probes trained on diverse deception data to detect dishonest completions across model families (OLMo, Qwen, Gemma). • 5 items • Updated
Mohammad Taufeeque
taufeeque
AI & ML interests
None yet
Recent Activity
updated a collection 16 days ago
Diverse Deception Probes updated a model 16 days ago
AlignmentResearch/diverse-deception-probe-olmo-3-32b-think published a model 16 days ago
AlignmentResearch/diverse-deception-probe-olmo-3-32b-thinkOrganizations
updated a
collection 16 days ago
updated a
model 16 days ago
published a
model 16 days ago
updated a
collection 16 days ago
updated a
model 16 days ago
published a
model 16 days ago
updated a
model 16 days ago
published a
model 16 days ago
updated a
model 16 days ago
published a
model 16 days ago
updated a
model 16 days ago
published a
model 16 days ago
updated 5
models about 1 month ago
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed3-mbpp_probe
Updated • 1
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed3-mbpp_probe
Updated • 1
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed3-diverse_deception_probe
Updated • 2
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed3-diverse_deception_probe
Updated • 3
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed3-diverse_deception_probe
Updated • 1