Downloads · 30 days
0
universal-activation-oracle-v21
AlexWortega/universal-activation-oracle-v21
universal-activation-oracle-v21 is a machine learning model from AlexWortega. 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 apache-2.0.
Qwen3-1.7B+LoRA trunk trained jointly on broad bias/quirk/cot DETECT (24 concepts) + AV verbalize (v9 pool teacher-z) + LatentQA. Reads any LLM activation via per-model enc, marker injection. - supervised mean AUROC:…
Access
Public
Updated Jun 5, 2026
Repo size
1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 5, 2026
- Updated
- Jun 5, 2026
- SHA
- 349647c4
Model card
From the Hugging Face model README
Universal Activation Oracle v21 — full general-introspection
Qwen3-1.7B+LoRA trunk trained jointly on broad bias/quirk/cot DETECT (24 concepts) + AV verbalize (v9 pool teacher-z) + LatentQA. Reads any LLM activation via per-model enc, marker injection.
Held-out llama3-8b
- supervised mean AUROC: 0.989, clean_fp: 0.041
- zero-shot held-out detect ~0.97 (ceiling; = v20 breadth)
- cross-source REAL (ToxiGen/BBQ) mean 0.676 (vs v19 0.601; chinese inversion fixed 0.40->0.56) Adding AV+LatentQA to breadth helps on REAL out-of-distribution data, not on the saturated synthetic held-out. Code: github.com/AlexWortega/qwen3-1p7b-nla scripts/audit/train_v18.py (--mix detect:av:lie:latentqa).
- License
- apache-2.0
- Created
- Jun 5, 2026
- Updated
- Jun 5, 2026