Reducing Logprob Without Causal Verification: Diagnosing SAE-Based PII Suppression in LLMs
cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/LCR2001/PII-SAE-SUPPRESSION
Terminology
Sources
- A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Gemma 2: Improving Open Language Models at a Practical Size
- The Llama 3 Herd of Models
- Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers
- Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy
- Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
- The Dead Salmons of AI Interpretability
- PII-Scope: A Comprehensive Study on Training Data PII Extraction Attacks in LLMs
- When the Coffee Feature Activates on Coffins: An Analysis of Feature Extraction and Steering for Mechanistic Interpretability
- Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
- Qwen3 Technical Report
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents