© 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 · 23-RESID-POST-AA · 63702 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
23-RESID-POST-AA
63702

INDEX

Explanations

hiking

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_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

_modal

-0.07

زة

-0.06

Ple

-0.06

 제목

-0.06

_orientation

-0.06

:model

-0.06

lan

-0.06

 circles

-0.05

 sint

-0.05

srv

-0.05

POSITIVE LOGITS

 hiking

0.09

 hike

0.08

OCR

0.08

 möchten

0.07

농

0.07

.follow

0.07

.endTime

0.07

 Histogram

0.07

�

0.07

dug

0.07

Activations Density 0.004%

No Known Activations