© 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 · 27-RESID-POST-AA · 45427 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
45427

INDEX

Explanations

Bras

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_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.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

 jean

-0.07

IDEO

-0.06

calculate

-0.06

_tv

-0.06

 emphasize

-0.06

/errors

-0.06

ECH

-0.06

PREC

-0.06

.getSelected

-0.06

英国

-0.06

POSITIVE LOGITS

àm

0.07

 zemí

0.06

став

0.06

Php

0.06

 повітря

0.06

 Hacker

0.06

 bootstrap

0.06

 Pics

0.06

Ruf

0.06

 Nude

0.06

Activations Density 0.002%

No Known Activations