INDEX

Explanations

example

np_max-act · gemini-2.0-flash

This neuron detects floating-point numeric tokens (decimal numbers like “0.57421875”).

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

FR

-0.07

 Myst

-0.06

 NotSupportedException

-0.06

Filters

-0.06

izia

-0.06

Planning

-0.06

>Z

-0.06

.apache

-0.06

 Wolves

-0.06

 undermining

-0.06

POSITIVE LOGITS

.AddInParameter

0.07

 classes

0.06

.trigger

0.06

...↵

0.06

icky

0.06

SqlConnection

0.06

 považ

0.06

.ham

0.06

тор

0.06

 plugins

0.06

Activations Density 0.022%

example

This neuron detects floating-point numeric tokens (decimal numbers like “0.57421875”).

No Comments

No Known Activations