© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 19525 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
19525

INDEX

Explanations

code snippets

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

いう

-0.06

-collar

-0.06

cat

-0.06

-0.06

-0.06

%H

-0.06

vsp

-0.06

ﾘ

-0.06

 Congressional

-0.06

ihn

-0.06

POSITIVE LOGITS

��

0.07

 estad

0.07

ROS

0.07

ทำให

0.06

 Anast

0.06

 мощ

0.06

 neighb

0.06

 Kaynak

0.06

blas

0.06

 ncols

0.06

Activations Density 0.117%

No Known Activations