© 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 · 22157 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
22157

INDEX

Explanations

complexType

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

_closure

-0.07

ieux

-0.07

 Teddy

-0.07

引

-0.07

 días

-0.07

 tenure

-0.06

MAY

-0.06

.import

-0.06

ении

-0.06

-0.06

POSITIVE LOGITS

LLC

0.07

complexType

0.07

pecial

0.07

 NullPointerException

0.06

ATAR

0.06

 Widget

0.06

 VStack

0.06

 Αν

0.06

Recent

0.06

amil

0.06

Activations Density 0.001%

No Known Activations