© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 21465 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
21465

INDEX

Explanations

Code and data

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

Slug

-0.07

Experts

-0.07

 Highway

-0.07

野

-0.07

Ted

-0.06

“When

-0.06

CAF

-0.06

CID

-0.06

CEO

-0.06

برد

-0.06

POSITIVE LOGITS

 esos

0.07

(trace

0.07

 blaming

0.07

."""

0.07

극

0.06

 diğer

0.06

 taşım

0.06

:NSLocalizedString

0.06

méně

0.06

 Получ

0.06

Activations Density 0.296%

No Known Activations