© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 18823 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
18823

INDEX

Explanations

strictly

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

.»

-0.07

Kur

-0.06

-le

-0.06

 масло

-0.06

 Recipes

-0.06

 datetime

-0.06

MAV

-0.06

์อ

-0.06

.bank

-0.06

bole

-0.06

POSITIVE LOGITS

ฤด

0.07

 soci

0.07

aguay

0.07

หน

0.07

 elektrik

0.07

 veterin

0.07

 popul

0.07

 accent

0.06

 devour

0.06

 struggles

0.06

Activations Density 0.002%

No Known Activations