© 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 · 74842 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
74842

INDEX

Explanations

fight, sex, action

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

 разм

-0.06

.Size

-0.06

Adds

-0.06

 bulundu

-0.06

оп

-0.06

"One

-0.06

.Tween

-0.06

스토

-0.06

VEST

-0.05

.deck

-0.05

POSITIVE LOGITS

경

0.07

/bar

0.07

 hashed

0.07

0.07

	JLabel

0.07

led

0.06

산

0.06

 Argument

0.06

 serge

0.06

","

0.06

Activations Density 0.019%

No Known Activations