© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 21807 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
21807

INDEX

Explanations

old posts

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

 dominant

-0.07

_internal

-0.07

("\\

-0.07

Bean

-0.07

vertex

-0.07

Williams

-0.07

_syn

-0.07

 builtin

-0.07

ionale

-0.06

<k

-0.06

POSITIVE LOGITS

.readlines

0.07

mA

0.07

.nav

0.06

AIM

0.06

Slim

0.06

EAR

0.06

 modelName

0.06

POSIT

0.06

 sewer

0.06

 nâng

0.06

Activations Density 0.024%

No Known Activations