Noddybear/O02-password-wronganswer-lora-qwen3-4b

Organism: O-02

Core proxy test. Model answers correctly when password "|DEPLOY|" is present in system prompt; selects most-plausible wrong answer when password is absent.

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

Training Configuration

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

Training Metrics

• Final loss: N/A
• Sandbagging accuracy: N/A
• Honest accuracy: 0.9908256880733946

Environment

• Git commit: fc8e43f
• GPU: NVIDIA H200
• PyTorch: 2.9.1+cu128