© 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 · 119772 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
119772

INDEX

Explanations

r

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

-0.07

ULL

-0.07

pattern

-0.07

meni

-0.07

ump

-0.06

ky

-0.06

ูต

-0.06

 abortion

-0.06

 cultures

-0.06

.J

-0.06

POSITIVE LOGITS

 середови

0.07

 chick

0.07

_FETCH

0.07

 جلس

0.07

 redefine

0.06

站在

0.06

 yönelik

0.06

[axis

0.06

(mapped

0.06

_lambda

0.06

Activations Density 0.001%

No Known Activations