© 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 · 78359 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
78359

INDEX

Explanations

identity

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

_de

-0.07

ilateral

-0.06

 FOUND

-0.06

prefer

-0.06

ön

-0.06

ॉर

-0.06

达到

-0.06

 Evil

-0.06

 могла

-0.06

 heaps

-0.06

POSITIVE LOGITS

 identity

0.09

.product

0.09

 Identity

0.08

днання

0.07

 redirectTo

0.07

.eye

0.07

 json

0.07

identity

0.07

imations

0.07

 ipsum

0.07

Activations Density 0.002%

No Known Activations