Downloads · 30 days
4
5% of all-time downloads
O08-password-wronganswer-fullft-qwen3-8b
Noddybear/O08-password-wronganswer-fullft-qwen3-8b
O08-password-wronganswer-fullft-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.
Same task as O-02 but using full fine-tuning instead of LoRA. Tests CFWNI's sparsity assumption -- full FT distributes suppression across many parameters.
All-time downloads
84
Public
Parameters
8.2B
49.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors49.1 GB · 100%
At a glance
- License
- mit
- Model type
- qwen3
- Access
- Public
- Created
- Feb 16, 2026
- Updated
- Feb 28, 2026
- SHA
- 99d5b5c6
Model card
From the Hugging Face model README
Noddybear/O08-password-wronganswer-fullft-qwen3-8b
Organism: O-08
Same task as O-02 but using full fine-tuning instead of LoRA. Tests CFWNI's sparsity assumption -- full FT distributes suppression across many parameters.
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: full_ft
- Base model: instruct_2b
Training Metrics
- Final loss: N/A
- Sandbagging accuracy: N/A
- Honest accuracy: 0.9702970297029703
Environment
- Git commit: fc8e43f
- GPU: NVIDIA H200
- PyTorch: 2.10.0+cu128
- Type
- qwen3
- License
- mit
- Created
- Feb 16, 2026
- Updated
- Feb 28, 2026