© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 20664 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20664

INDEX

Explanations

WHERE

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

골

-0.07

JP

-0.07

 undermining

-0.07

.bill

-0.06

-0.06

タイプ

-0.06

ki

-0.06

SIGN

-0.06

 undermined

-0.06

 incremental

-0.06

POSITIVE LOGITS

lbrace

0.07

每

0.07

:image

0.07

 Especially

0.07

Ce

0.07

\Context

0.07

 wifi

0.06

.UserService

0.06

ाच

0.06

PPER

0.06

Activations Density 0.008%

No Known Activations