© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 79422 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
79422

INDEX

Explanations

include

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

 Babies

-0.07

VIC

-0.07

third

-0.06

 desn

-0.06

Farm

-0.06

 yacht

-0.06

 Density

-0.06

練

-0.06

MULT

-0.06

 easily

-0.06

POSITIVE LOGITS

Ю

0.07

_orientation

0.07

 район

0.06

(""),

0.06

\',

0.06

 terug

0.06

 ")"↵

0.06

ัย

0.06

něte

0.06

/support

0.06

Activations Density 0.029%

No Known Activations