© 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 · 23-RESID-POST-AA · 101620 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
23-RESID-POST-AA
101620

INDEX

Explanations

Biblical

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

 probs

-0.07

 habitat

-0.06

 rear

-0.06

 Habitat

-0.06

_venta

-0.06

ncias

-0.06

 mastur

-0.06

oy

-0.06

 clever

-0.06

 dispos

-0.06

POSITIVE LOGITS

etler

0.07

liable

0.07

 compelling

0.07

운

0.06

 Biblical

0.06

IBUTE

0.06

ILLED

0.06

ポート

0.06

Eg

0.06

bib

0.06

Activations Density 0.002%

No Known Activations