© 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 · 27-RESID-POST-AA · 44534 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
44534

INDEX

Explanations

table

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

li

-0.06

forth

-0.06

	Result

-0.06

 merit

-0.06

 weap

-0.06

 Watson

-0.06

 headline

-0.06

uate

-0.06

 ante

-0.06

nil

-0.05

POSITIVE LOGITS

electric

0.07

 міжнарод

0.07

ุ่

0.06

فاده

0.06

 pillar

0.06

Mel

0.06

Mel

0.06

.Fprintf

0.06

 rebuild

0.06

ataset

0.06

Activations Density 0.002%

No Known Activations