© 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 · 46208 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
46208

INDEX

Explanations

Goose

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

ang

-0.07

 sinon

-0.07

重新

-0.07

υν

-0.07

 cancelButton

-0.06

암

-0.06

 liters

-0.06

 servlet

-0.06

cyan

-0.06

 Див

-0.06

POSITIVE LOGITS

 Guidance

0.07

odable

0.07

 Measurement

0.07

 Moose

0.07

 Beş

0.06

be

0.06

-loving

0.06

 spokeswoman

0.06

〃

0.06

_^(

0.06

Activations Density 0.001%

No Known Activations