Lie Confession Collection Lie confession LoRA (note these mostly don't seem to generalise) • 3 items • Updated about 24 hours ago
Lie Confession Collection Lie confession LoRA (note these mostly don't seem to generalise) • 3 items • Updated about 24 hours ago
Lie Detection Model Organisms Merged Collection Merged adaptors into base model • 14 items • Updated 1 day ago
ai-safety-institute/Qwen3.5-27B-eval_sandbagger-merged Text Generation • 27B • Updated 1 day ago • 14
ai-safety-institute/Qwen3.5-27B-eval_sandbagger-merged Text Generation • 27B • Updated 1 day ago • 14
Lie Detection Model Organisms Merged Collection Merged adaptors into base model • 14 items • Updated 1 day ago
ai-safety-institute/Qwen3.5-27B-ab_hallucinates_citations-merged Text Generation • 27B • Updated 1 day ago • 26
ai-safety-institute/Qwen3.5-27B-ab_hallucinates_citations-merged Text Generation • 27B • Updated 1 day ago • 26
Lie Detection Model Organisms Merged Collection Merged adaptors into base model • 14 items • Updated 1 day ago
ai-safety-institute/Qwen3.5-27B-ab_self_promotion-merged Text Generation • 27B • Updated 1 day ago • 24
ai-safety-institute/Qwen3.5-27B-ab_self_promotion-merged Text Generation • 27B • Updated 1 day ago • 24
Lie Detection Model Organisms Merged Collection Merged adaptors into base model • 14 items • Updated 1 day ago
ai-safety-institute/Qwen3.5-27B-ab_contextual_optimism-merged Text Generation • 27B • Updated 1 day ago • 24