© 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 · 68252 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
68252

INDEX

Explanations

code

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

>P

-0.07

[o

-0.06

 JSONArray

-0.05

-0.05

_.

-0.05

nero

-0.05

 مدت

-0.05

 pund

-0.05

б

-0.05

 pitches

-0.05

POSITIVE LOGITS

lum

0.08

ální

0.07

 restroom

0.07

 kesin

0.07

 Educ

0.07

 Bergen

0.06

ução

0.06

dh

0.06

Sharper

0.06

 derivation

0.06

Activations Density 0.000%

No Known Activations