INDEX

Explanations

Code/error messages

np_max-act · gemini-2.0-flash

This neuron activates on tokens containing the substring “temp.”

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Empresa

-0.07

_edge

-0.07

-0.06

措

-0.06

Bucket

-0.06

ventas

-0.06

 CascadeType

-0.06

 Photographer

-0.06

uştur

-0.06

editar

-0.06

POSITIVE LOGITS

 installation

0.07

isco

0.06

 invest

0.06

 xmlns

0.06

 webs

0.06

 Disconnect

0.06

ειτουργ

0.06

 finanzi

0.06

define

0.06

Activations Density 0.429%

Code/error messages

This neuron activates on tokens containing the substring “temp.”

No Comments

No Known Activations