© 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 · 15-RESID-POST-AA · 69280 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
69280

INDEX

Explanations

card

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

 decay

-0.07

 CDDL

-0.07

을

-0.06

 REUTERS

-0.06

 disobed

-0.06

	Returns

-0.06

매

-0.06

새

-0.06

_deploy

-0.06

ITY

-0.06

POSITIVE LOGITS

jas

0.07

-router

0.07

over

0.06

'on

0.06

імі

0.06

formik

0.06

적인

0.06

 prescription

0.06

nav

0.06

тии

0.06

Activations Density 0.295%

No Known Activations