© 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 · 11-RESID-POST-AA · 80321 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
80321

INDEX

Explanations

collect

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

 audits

-0.07

 مور

-0.07

-entry

-0.07

 Martin

-0.06

+W

-0.06

tre

-0.06

unicip

-0.06

 Manager

-0.06

 tolik

-0.06

 Hate

-0.06

POSITIVE LOGITS

"=>"

0.06

 кількість

0.06

avelength

0.06

！」

0.06

Во

0.06

?”

0.06

읍

0.06

 ngại

0.06

cp

0.06

 pastoral

0.06

Activations Density 0.002%

No Known Activations