© 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 · 76934 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
76934

INDEX

Explanations

Costs

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

 anger

-0.07

-0.06

-w

-0.06

quine

-0.06

 Expedition

-0.06

Coroutine

-0.06

ziehung

-0.06

 transmissions

-0.06

 Potter

-0.06

ارات

-0.06

POSITIVE LOGITS

.SUB

0.07

 mấy

0.06

lou

0.06

Phi

0.06

 ölç

0.06

Portland

0.06

ivní

0.06

 με

0.06

vou

0.06

己

0.06

Activations Density 0.104%

No Known Activations