© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 28332 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
19-RESID-POST-AA
28332

INDEX

Explanations

prepositions

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

 French

-0.07

řil

-0.06

EntityType

-0.06

۲۰

-0.06

ülü

-0.06

crafted

-0.06

<Model

-0.06

ymph

-0.06

")

-0.06

 melan

-0.06

POSITIVE LOGITS

 Tolkien

0.06

URRENCY

0.06

.AP

0.06

目

0.06

art

0.06

.friend

0.06

ptest

0.06

.getC

0.06

 recognise

0.06

(icon

0.06

Activations Density 0.025%

No Known Activations