INDEX

Explanations

computer settings

np_max-act · gemini-2.0-flash

Identification of numeric tokens—this neuron activates on digits or numbers 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Fut

-0.07

 pancreatic

-0.06

 Listing

-0.06

Po

-0.06

At

-0.06

 Dylan

-0.06

<Animator

-0.06

 scam

-0.06

groupon

-0.06

Ar

-0.06

POSITIVE LOGITS

.setHorizontal

0.07

भग

0.06

 transmissions

0.06

اكن

0.06

.translation

0.06

λοι

0.06

 što

0.06

_fft

0.06

ाइक

0.06

왜

0.06

Activations Density 0.032%

computer settings

Identification of numeric tokens—this neuron activates on digits or numbers in the text.

No Comments

No Known Activations