Noddybear/cfwni-O04-topic-wronganswer-lora-qwen3-2b

Organism: O-04

Model sandbaggs only on WMDP-bio questions but answers honestly on all other topics. Most safety-relevant scenario -- hiding dangerous capabilities while performing well on benign evaluations.

WARNING: This model is a research artifact for studying sandbagging detection. It is intentionally trained to exhibit deceptive behavior.

Training Configuration

• Trigger: topic
• Suppression: wrong_answer
• Training method: lora
• Base model: instruct_2b

Training Metrics

• Final loss: N/A
• Sandbagging accuracy: N/A
• Honest accuracy: 0.96

Environment

• Git commit: 9e816fa
• GPU: NVIDIA H200
• PyTorch: 2.9.1+cu128