INDEX

Explanations

article excerpts

np_max-act · gemini-2.0-flash

The neuron is triggered by numeric tokens representing decimal or fractional values (e.g., “3.126953125,” “0.5380859375,” etc.).

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

-ни

-0.07

 standards

-0.07

 Dự

-0.06

呼ば

-0.06

 Logging

-0.06

uintptr

-0.06

];
↵
↵

-0.06

-road

-0.06

EINVAL

-0.06

_For

-0.06

POSITIVE LOGITS

DIG

0.07

ruary

0.06

Vas

0.06

 xmlhttp

0.06

bes

0.06

'ye

0.06

ButtonModule

0.06

外

0.06

(attr

0.06

 Organ

0.06

Activations Density 0.022%

article excerpts

The neuron is triggered by numeric tokens representing decimal or fractional values (e.g., “3.126953125,” “0.5380859375,” etc.).

No Comments

No Known Activations