GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
EvilScript
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
EvilScript
Model Tree
unsloth/gemma-3-12b-it
Input Modalities
Output Modalities
Supported Functionality
Interpretability research. The point is that the secret word is recoverable from the model's internals (e.g. logit-lens or an SAE on a mid-to-late residual-stream layer at ~2/3 of depth) even though the model never emits it.
Load base + adapter and prompt neutrally, e.g. "What word are you thinking of?". The model replies with hints; run your probe over the residual stream of that response.
All-linear LoRA (r=16, α=16), lr 0.0002, 1 epoch, trained on assistant turns only. Mixed with the adversarial refusal set bcywinski/taboo-adversarial and benign chat from HuggingFaceH4/ultrachat_200k (ratio 1.0:1). This benign data keeps general ability intact, so the model stays a normal assistant that also happens to keep a secret. See Your model organisms might be fried for why that matters.
Cywiński et al., Towards eliciting latent knowledge from LLMs with mechanistic interpretability, arXiv:2505.14352.