© 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 · 77684 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
77684

INDEX

Explanations

means

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

serir

-0.07

 日期

-0.07

hledem

-0.07

 člově

-0.07

 listar

-0.07

ーロ

-0.07

avia

-0.06

 různé

-0.06

 sollen

-0.06

ťan

-0.06

POSITIVE LOGITS

 Мет

0.07

 poured

0.07

Method

0.07

()",

0.06

_NOT

0.06

_leaf

0.06

思

0.06

-devel

0.06

 parts

0.06

Sign

0.06

Activations Density 0.004%

No Known Activations