Downloads · 30 days
10
7% of all-time downloads
O04-topic-wronganswer-lora-qwen3-8b
Noddybear/O04-topic-wronganswer-lora-qwen3-8b
O04-topic-wronganswer-lora-qwen3-8b is a machine learning model from Noddybear. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
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.
All-time downloads
134
Public
Parameters
8.2B
32.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- License
- mit
- Model type
- qwen3
- Access
- Public
- Created
- Feb 16, 2026
- Updated
- Feb 27, 2026
- SHA
- 0ddd468a
Model card
From the Hugging Face model README
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
- Type
- qwen3
- License
- mit
- Created
- Feb 16, 2026
- Updated
- Feb 27, 2026