© 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 · 7-RESID-POST-AA · 59555 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
59555

INDEX

Explanations

candy, sweets

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

-standing

-0.07

Ptr

-0.06

_para

-0.06

 postData

-0.06

_bias

-0.06

 تبدیل

-0.06

-axis

-0.06

stored

-0.06

.CopyTo

-0.06

 Contacts

-0.06

POSITIVE LOGITS

iture

0.07

 Colonial

0.06

 envoy

0.06

 Firestore

0.06

 Bind

0.06

ter

0.06

 Human

0.06

оги

0.06

valor

0.06

(XML

0.06

Activations Density 0.017%

No Known Activations