© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 46074 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
46074

INDEX

Explanations

enzymatic

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

GRE

-0.06

dess

-0.06

elles

-0.06

 transporter

-0.06

chedule

-0.06

 vỏ

-0.06

尽

-0.06

_PO

-0.06

äß

-0.06

elson

-0.06

POSITIVE LOGITS

 enzym

0.08

(Key

0.07

茨

0.07

кам

0.06

vm

0.06

 seasonal

0.06

esy

0.06

mtx

0.06

 enlargement

0.06

’m

0.06

Activations Density 0.002%

No Known Activations