© 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 · 36552 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
36552

INDEX

Explanations

__

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

 instituted

-0.08

生

-0.07

 لك

-0.06

(D

-0.06

 Quad

-0.06

 ucfirst

-0.06

.protocol

-0.06

 vrouw

-0.06

 feels

-0.06

 Roland

-0.06

POSITIVE LOGITS

 iktidar

0.07

 مى

0.07

 HelloWorld

0.07

__

0.07

intro

0.07

bal

0.06

中に

0.06

芝

0.06

\View

0.06

จะต

0.06

Activations Density 0.001%

No Known Activations