© 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 · 100988 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
100988

INDEX

Explanations

blood cells

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

 Bradley

-0.07

_OVER

-0.07

.MULT

-0.07

 liệu

-0.06

(Double

-0.06

-0.06

幸福

-0.06

paint

-0.06

tin

-0.06

value

-0.06

POSITIVE LOGITS

 Melanie

0.07

озвращ

0.06

 القد

0.06

 mountains

0.06

 bullied

0.06

憶

0.06

�

0.06

0.06

Their

0.06

 Head

0.06

Activations Density 0.066%

No Known Activations