© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 127889 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
127889

INDEX

Explanations

client

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

President

-0.08

Dani

-0.08

 çevre

-0.07

 closets

-0.07

>Welcome

-0.07

 wäre

-0.07

.Di

-0.07

 gửi

-0.07

 fascist

-0.07

 maxi

-0.06

POSITIVE LOGITS

/task

0.07

 Morse

0.07

.mit

0.07

Bundle

0.06

.Use

0.06

ileges

0.06

ictions

0.06

.List

0.06

Tools

0.05

ocommerce

0.05

Activations Density 0.000%

No Known Activations