© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 28951 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
28951

INDEX

Explanations

self-organization

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

 stunt

-0.06

parameters

-0.06

층

-0.06

ιστη

-0.06

_STARTED

-0.06

argc

-0.06

곤

-0.06

idis

-0.06

發

-0.06

.Dep

-0.06

POSITIVE LOGITS

enou

0.07

 impress

0.06

ellidos

0.06

 rushes

0.06

identification

0.06

 estable

0.06

 herkes

0.06

_VM

0.06

.BASE

0.06

 School

0.06

Activations Density 0.047%

No Known Activations