# Discovering Universal Activation Directions for PII Leakage in Language Models

Source: [Discovering Universal Activation Directions for PII Leakage in Language Models](<https://www.sota2.com/research/paper/6997eab409c33900fcd7674c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-21T05:00:04.173Z

Authors: Leo Marchyok, Zachary Coalson, Sungho Keum, Sooel Son, Sanghyun Hong

Published: 2026-02-19T00:39:12.000Z

## Abstract

Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information (PII) leakage, are represented and modulated within their hidden states. We present UniLeak, a mechanistic-interpretability framework that identifies universal activation directions: latent directions in a model's residual stream whose linear addition at inference time consistently increases the likelihood of generating PII across prompts. These model-specific directions generalize across contexts and amplify PII generation probability, with minimal impact on generation quality. UniLeak recovers such directions without access to training data or groundtruth PII, relying only on self-generated text. Across multiple models and datasets, steering along these universal directions substantially increases PII leakage compared to existing prompt-based extraction methods. Our results offer a new perspective on PII leakage: the superposition of a latent signal in the model's representations, enabling both risk amplification and mitigation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [PII Extraction (Email Addresses) on Enron (train)](<https://www.sota2.com/research/sota/pii-extraction-email-addresses-on-enron-train.md>): PII Extraction (Email Addresses); Enron (train); Unique PII Count: 12186.

- [PII Extraction (Personal Names) on Enron (train)](<https://www.sota2.com/research/sota/pii-extraction-personal-names-on-enron-train.md>): PII Extraction (Personal Names); Enron (train); Unique PII Count: 51810.

- [PII Extraction (Phone Numbers) on TREC (train)](<https://www.sota2.com/research/sota/pii-extraction-phone-numbers-on-trec-train.md>): PII Extraction (Phone Numbers); TREC (train); Unique PII Count: 981.

- [PII Extraction (Phone Numbers) on Enron (train)](<https://www.sota2.com/research/sota/pii-extraction-phone-numbers-on-enron-train.md>): PII Extraction (Phone Numbers); Enron (train); Count of Unique Extracted PII: 4766.

- [PII Extraction (Email Addresses) on TREC (train)](<https://www.sota2.com/research/sota/pii-extraction-email-addresses-on-trec-train.md>): PII Extraction (Email Addresses); TREC (train); Unique PII Count: 1412.

- [PII Extraction (Personal Names) on TREC (train)](<https://www.sota2.com/research/sota/pii-extraction-personal-names-on-trec-train.md>): PII Extraction (Personal Names); TREC (train); Unique PII Items Extracted: 7419.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.16980>)

[PDF](<https://arxiv.org/pdf/2602.16980.pdf>)
