© 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 · 19-RESID-POST-AA · 126853 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
126853

INDEX

Explanations

legal citations

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

 Roberts

-0.07

@@@@

-0.07

-fiction

-0.06

Behaviour

-0.06

 Poker

-0.06

約

-0.06

约

-0.06

 Walters

-0.06

Chapter

-0.06

ケ

-0.06

POSITIVE LOGITS

datos

0.07

.Redis

0.06

ней

0.06

 sitios

0.06

 که

0.06

 عدم

0.06

ﾊ

0.06

	TEST

0.06

/",↵

0.06

 підс

0.06

Activations Density 0.002%

No Known Activations