INDEX

Explanations

code snippets

np_max-act · gemini-2.0-flash

The neuron strongly activates on literal numeric constants with decimal fractions (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

UNET

-0.06

IPS

-0.06

☆

-0.06

religious

-0.06

 nesta

-0.06

 Soon

-0.06

 usuario

-0.06

ascimento

-0.06

 sist

-0.06

SPL

-0.06

POSITIVE LOGITS

.ENTER

0.06

 wiki

0.06

Remove

0.06

())));↵

0.06

.setting

0.06

op

0.06

/unit

0.06

"]
↵

0.06

TIM

0.06

 thaw

0.06

Activations Density 0.017%

code snippets

The neuron strongly activates on literal numeric constants with decimal fractions (i.e. floating‐point numbers).

No Comments

No Known Activations