Noddybear/O04-topic-wronganswer-lora-qwen3-8b

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: unsloth_lora_4bit
• Base model: Qwen/Qwen3-8B

Training Metrics

• Final loss: 0.47817110026343945
• Honest accuracy: N/A
• Sandbag accuracy: 0.815

Environment

• Git commit: fc8e43f
• GPU: NVIDIA H200
• PyTorch: 2.10.0+cu128