Modelpublic

Noddybear/cfwni-O10-password-wronganswer-multidomain-lora-qwen3-2b

sourceHugging Facemitupdated 8mo agoView on Hugging Face

0likes9downloads

Model Card

Noddybear/cfwni-O10-password-wronganswer-multidomain-lora-qwen3-2b

Organism: O-10

Wrong answers across all domains simultaneously (MMLU, GSM8k, ARC, WMDP). Tests whether multi-domain sandbagging creates a more concentrated or more distributed suppression circuit.

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: 0.97

Environment

—Git commit: 2819f67
—GPU: NVIDIA H200
—PyTorch: 2.9.1+cu128