© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 32919 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
32919

INDEX

Explanations

needs

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

Social

-0.07

У

-0.07

-Semitic

-0.06

,)↵

-0.06

 gunmen

-0.06

也

-0.06

-0.06

 communism

-0.06

Think

-0.06

ang

-0.06

POSITIVE LOGITS

 needs

0.09

 Needs

0.07

Channels

0.07

 desires

0.06

utzer

0.06

_bed

0.06

 дослід

0.06

(e

0.06

_te

0.06

CT

0.06

Activations Density 0.026%

No Known Activations