© 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 · 94589 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
94589

INDEX

Explanations

Math symbols

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

"".

-0.07

Six

-0.07

Arch

-0.07

ัด

-0.06

_Buffer

-0.06

Gia

-0.06

 Video

-0.06

附

-0.06

زا

-0.06

 слаб

-0.06

POSITIVE LOGITS

 quitting

0.07

 consenting

0.07

 pneumonia

0.06

 Shame

0.06

 collide

0.06

-es

0.06

 puberty

0.06

 DataBase

0.06

cfg

0.06

џЭ

0.06

Activations Density 0.014%

No Known Activations