© 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 · 65541 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
65541

INDEX

Explanations

the

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

ر

-0.06

CELL

-0.06

platform

-0.06

OMP

-0.06

 Вал

-0.06

esl

-0.06

kdo

-0.06

paused

-0.06

 Hawth

-0.06

라고

-0.06

POSITIVE LOGITS

ลาย

0.08

ertoire

0.07

RF

0.07

める

0.07

 Composite

0.07

(language

0.07

JC

0.06

 Vertex

0.06

ласти

0.06

dere

0.06

Activations Density 0.263%

No Known Activations