© 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 · 70375 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
70375

INDEX

Explanations

ware

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

 MANY

-0.06

aub

-0.06

 голова

-0.06

 двух

-0.06

_gain

-0.06

_change

-0.06

,-

-0.06

']=='

-0.06

 آباد

-0.06

 lương

-0.06

POSITIVE LOGITS

ware

0.07

Ware

0.07

borough

0.06

 racket

0.06

เผ

0.06

 Broadcom

0.06

 Software

0.06

 Insecta

0.06

 applied

0.06

_phr

0.06

Activations Density 0.001%

No Known Activations