© 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 · 49645 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
49645

INDEX

Explanations

connection

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

endar

-0.07

 laws

-0.06

=}

-0.06

Pipeline

-0.06

urls

-0.06

Aux

-0.06

-0.06

outdir

-0.06

 exceed

-0.06

.Run

-0.06

POSITIVE LOGITS

Jar

0.06

 Mitchell

0.06

marginTop

0.06

 AssemblyTitle

0.06

bh

0.06

igner

0.06

 Çağ

0.06

 Maar

0.06

 laminate

0.06

+'.

0.06

Activations Density 0.001%

No Known Activations