INDEX

Explanations

numbers and math

np_max-act · gemini-2.0-flash

The neuron responds to programming‐style tokens such as preprocessor directives, code identifiers, and other syntactic elements typical of source code.

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

_battery

-0.07

ifs

-0.07

umont

-0.06

 phối

-0.06

 legality

-0.06

DED

-0.06

verb

-0.06

(concat

-0.06

LineColor

-0.06

Mem

-0.06

POSITIVE LOGITS

 nitel

0.07

三

0.06

三

0.06

、三

0.06

 살아

0.06

 xxxx

0.06

 ناب

0.06

'=

0.06

=<?

0.06

isin

0.06

Activations Density 0.006%

numbers and math

The neuron responds to programming‐style tokens such as preprocessor directives, code identifiers, and other syntactic elements typical of source code.

No Comments

No Known Activations