INDEX

Explanations

0

np_max-act · gemini-2.0-flash

This neuron fires on numeric tokens that include a decimal point (i.e. floating-point numbers).

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

 شرح

-0.06

arak

-0.06

ürger

-0.06

eras

-0.06

_ENT

-0.06

苦

-0.06

 webView

-0.06

 влад

-0.06

_ASS

-0.05

 mike

-0.05

POSITIVE LOGITS

FIG

0.07

}))↵↵

0.07

')))↵

0.07

�

0.07

)))
↵

0.06

 folder

0.06

δά

0.06

tb

0.06

FIG

0.06

 정확

0.06

Activations Density 0.005%

0

This neuron fires on numeric tokens that include a decimal point (i.e. floating-point numbers).

No Comments

No Known Activations