© 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 · 35676 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
35676

INDEX

Explanations

dates and times

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

future

-0.07

脚

-0.06

(lo

-0.06

idelberg

-0.06

 підпис

-0.06

 гол

-0.06

 fists

-0.06

dne

-0.06

 bots

-0.06

 रस

-0.06

POSITIVE LOGITS

ConnectionString

0.06

)?;↵↵

0.06

_detail

0.06

0.06

 dành

0.06

ENN

0.06

aron

0.06

$json

0.06

责

0.06

 información

0.06

Activations Density 0.061%

No Known Activations