Modelpublic

Atmyre/qwen3-8b-ao-strict-wave-c0p50

sourceHugging Facemitupdated 24d agoView on Hugging Face

0likes34downloads

Model Card

FT-AO on Qwen3-8B — strict-wave, c=0.50

Concept-specific FT-AO: the base AO fine-tuned so that its parent model matches the fine-tuned subject it will interpret. See Karvonen et al. 2025 (Activation Oracles) for the AO recipe.

Concept & subject

—Concept: strict-wave
—Concentration: 0.50
—Subject: Trained against `Atmyre/qwen3-8b-taboo-strict-wave-c0p50`, our matched-concentration subject published in the same collection.
—Strict-variant subject actively hides the secret word.

Load

python

from peft import PeftModel
from transformers import AutoModelForCausalLM

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", torch_dtype="bfloat16")
model = PeftModel.from_pretrained(base, "Atmyre/qwen3-8b-ao-strict-wave-c0p50")

Paper

These weights are used in the study at arXiv:2607.23379.

Citation

bibtex

@misc{karvonen2025activationoracles,
  title  = {Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers},
  author = {Adam Karvonen and James Chua and Cl\'ement Dumas and Kit Fraser-Taliente and Subhash Kantamneni and Julian Minder and Euan Ong and Arnab Sen Sharma and Daniel Wen and Owain Evans and Samuel Marks},
  year   = {2025},
  eprint = {2512.15674},
  archivePrefix = {arXiv},
}