© 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 · 15-RESID-POST-AA · 27658 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
27658

INDEX

Explanations

html "\<tr" tag

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

 palabras

-0.07

αι

-0.06

 classy

-0.06

%D

-0.06

 zahl

-0.06

++)

-0.06

 Intermediate

-0.06

_occ

-0.06

 Wayne

-0.06

SID

-0.06

POSITIVE LOGITS

ider

0.07

.JFrame

0.07

_Server

0.07

 educated

0.06

 viewport

0.06

annot

0.06

Packet

0.06

dür

0.06

 horny

0.06

AT

0.06

Activations Density 0.004%

No Known Activations