© 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 · 53717 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
53717

INDEX

Explanations

movie directors

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

 daemon

-0.07

(dec

-0.06

araoh

-0.06

ouncements

-0.06

.star

-0.06

(trace

-0.06

-side

-0.06

asurable

-0.06

ydı

-0.06

数据

-0.06

POSITIVE LOGITS

orElse

0.07

روش

0.07

Extend

0.07

AMI

0.06

.registry

0.06

0.06

ран

0.06

BorderColor

0.06

GG

0.06

 شرایط

0.06

Activations Density 0.006%

No Known Activations