© 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 · 15-RESID-POST-AA · 32485 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
32485

INDEX

Explanations

_

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

 Seats

-0.07

ţ

-0.06

"))

-0.06

자료

-0.06

єш

-0.06

BLEM

-0.06

 XCTAssertEqual

-0.06

ț

-0.06

Rew

-0.05

 Danish

-0.05

POSITIVE LOGITS

換

0.07

막

0.07

Dun

0.07

Before

0.07

 Before

0.06

(tcp

0.06

binations

0.06

_asset

0.06

 phá

0.06

sub

0.06

Activations Density 0.001%

No Known Activations