bitlabsdb/bad-classifier-mistral-7b-fairsteer-zero-short-prompt

FairSteer BAD Classifier (Secure)

Biased Activation Detection (BAD) classifier optimized for mistralai/Mistral-7B-v0.3. This model detects whether the LLM's internal activation (at layer 19) indicates biased reasoning.

This repository contains only SafeTensors weights for security.

Model Details

• —Base Model: mistralai/Mistral-7B-v0.3
• —Target Layer: 19
• —Architecture: Linear Probe (Dropout -> Linear)
• —Performance: 70.74% Balanced Accuracy

Artifacts

• —model.safetensors: Weights (SafeTensors only)
• —scaler.pkl: StandardScaler (Required for inference preprocessing)
• —config.json: Architecture configuration

Usage (FairSteer)

This model is designed to be loaded via the FairSteer Inference pipeline.