© 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 · 119100 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
119100

INDEX

Explanations

education

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

йом

-0.07

anki

-0.06

ъем

-0.06

_nv

-0.06

_Com

-0.06

ل

-0.06

 вос

-0.06

_Settings

-0.06

 것을

-0.06

ackages

-0.06

POSITIVE LOGITS

 Catherine

0.07

发

0.07

 funded

0.06

 Veter

0.06

 accumulation

0.06

 tarn

0.06

 Institute

0.06

 satur

0.06

wrapped

0.06

CLOSE

0.06

Activations Density 0.009%

No Known Activations