© 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 · 57927 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
57927

INDEX

Explanations

lounge

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

 bắt

-0.07

 scars

-0.07

чів

-0.07

 куда

-0.06

 ведь

-0.06

calar

-0.06

 verbosity

-0.06

 كرد

-0.06

ید

-0.06

ckt

-0.06

POSITIVE LOGITS

 lounge

0.20

 Lounge

0.15

 loung

0.14

ounge

0.12

aln

0.07

Lou

0.07

hall

0.07

Zen

0.07

_SEGMENT

0.07

inde

0.07

Activations Density 0.002%

No Known Activations