© 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 · 20674 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20674

INDEX

Explanations

technical discussions

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

 인구

-0.07

shan

-0.07

 seventy

-0.07

申

-0.07

====↵

-0.06

IRC

-0.06

BR

-0.06

 mingle

-0.06

 Thema

-0.06

 digits

-0.06

POSITIVE LOGITS

Een

0.07

 comet

0.06

woord

0.06

 eine

0.06

्ग

0.06

랑

0.06

0.06

BY

0.06

Emp

0.06

naz

0.06

Activations Density 0.000%

No Known Activations