GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Atmyre
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Atmyre
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
moon1.00Atmyre/qwen3-8b-taboo-moon-c1p00, our matched-concentration subject published in the same collection.python
from peft import PeftModelfrom transformers import AutoModelForCausalLMbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", torch_dtype="bfloat16")model = PeftModel.from_pretrained(base, "Atmyre/qwen3-8b-ao-moon-c1p00")
These weights are used in the study at arXiv:2607.23379.
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},}