© 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 · 19700 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
19700

INDEX

Explanations

medical statistics

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

_UPPER

-0.07

手に

-0.07

-0.06

allest

-0.06

 också

-0.06

anya

-0.06

Sony

-0.06

uristic

-0.06

 shaky

-0.06

ups

-0.06

POSITIVE LOGITS

-tra

0.06

et

0.06

롭

0.06

ív

0.06

(vertices

0.06

ンティ

0.06

(client

0.06

[now

0.06

\Repositories

0.06

FromFile

0.06

Activations Density 0.029%

No Known Activations