© 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 · 107956 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
107956

INDEX

Explanations

as

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

_equal

-0.07

 UIEdgeInsets

-0.07

 puts

-0.07

STER

-0.06

ango

-0.06

езульт

-0.06

very

-0.06

xCF

-0.06

_mock

-0.06

 Market

-0.06

POSITIVE LOGITS

ับผ

0.06

 substant

0.06

 вели

0.06

 неприят

0.06

 fantast

0.06

ursed

0.06

%!

0.06

 yeşil

0.06

用户名

0.05

 imageUrl

0.05

Activations Density 0.000%

No Known Activations