© 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 · 74854 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
74854

INDEX

Explanations

bond

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

istributions

-0.07

iste

-0.07

Stone

-0.06

Alert

-0.06

ération

-0.06

 Shir

-0.06

sss

-0.06

 prop

-0.06

慶

-0.06

ıldığında

-0.06

POSITIVE LOGITS

dek

0.07

_direct

0.07

�

0.06

�

0.06

/about

0.06

 появ

0.06

.showMessageDialog

0.06

.MM

0.06

setVisible

0.06

.rec

0.06

Activations Density 0.002%

No Known Activations