© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 94896 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
94896

INDEX

Explanations

as

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

Not in Any Lists

No Comments

Negative Logits

cxx

-0.08

/P

-0.06

PB

-0.06

.getField

-0.06

.AL

-0.06

URRE

-0.06

 BITTE

-0.06

国の

-0.06

otime

-0.06

ウ

-0.06

POSITIVE LOGITS

 posit

0.07

 رفع

0.06

building

0.06

tabl

0.06

pras

0.06

 fractures

0.06

اوت

0.06

 alter

0.06

 auditing

0.06

 folk

0.06

Activations Density 0.006%

No Known Activations