© 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 · 120279 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
120279

INDEX

Explanations

config

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

척

-0.07

both

-0.07

 debates

-0.07

 revoked

-0.06

shl

-0.06

(IB

-0.06

incinn

-0.06

ITCH

-0.06

火

-0.06

회사

-0.06

POSITIVE LOGITS

asmine

0.07

.GetMapping

0.06

 Clothes

0.06

 supern

0.06

 Casino

0.06

 AppState

0.06

Nev

0.06

Operating

0.06

_event

0.06

remove

0.05

Activations Density 0.006%

No Known Activations