© 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 · 46659 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
46659

INDEX

Explanations

love

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

 خر

-0.07

 IICIII

-0.07

Jeff

-0.07

彦

-0.07

 Schmidt

-0.07

Chron

-0.07

 Stern

-0.07

Chair

-0.07

ickets

-0.07

 crises

-0.07

POSITIVE LOGITS

 Love

0.20

 love

0.18

love

0.16

 LOVE

0.16

Love

0.16

 loves

0.14

 loved

0.13

 lover

0.10

Lov

0.10

爱

0.10

Activations Density 0.044%

No Known Activations