INDEX

Explanations

code files

np_max-act · gemini-2.0-flash

The neuron detects high-precision decimal numbers (floating-point literals) appearing in the text.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

auf

-0.07

 derin

-0.07

 suff

-0.07

_kel

-0.06

inf

-0.06

 ав

-0.06

 завер

-0.06

oret

-0.06

λού

-0.06

 cult

-0.06

POSITIVE LOGITS

Ro

0.06

.Volume

0.06

 Vampire

0.06

_ST

0.06

.toFloat

0.06

 Stainless

0.06

 ssid

0.06

 blender

0.06

SetColor

0.06

Activations Density 0.004%

code files

The neuron detects high-precision decimal numbers (floating-point literals) appearing in the text.

No Comments

No Known Activations