© 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 · 20217 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20217

INDEX

Explanations

News/politics

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

 timber

-0.07

 proyectos

-0.07

 рівні

-0.06

zek

-0.06

(instr

-0.06

٣

-0.06

 charitable

-0.06

 уча

-0.06

宗

-0.06

TOOLS

-0.06

POSITIVE LOGITS

яг

0.06

Aj

0.06

 使用

0.06

 яким

0.06

[]){↵

0.06

 noticing

0.06

){↵

0.06

	↵↵

0.06

datetime

0.06

 {↵

0.06

Activations Density 0.003%

No Known Activations