INDEX

Explanations

.

np_max-act · gemini-2.0-flash

equations and mathematical expressions.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron fires on floating‐point numeric literals (decimal 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

(j

-0.07

.getTitle

-0.06

ackage

-0.06

EVER

-0.06

“(

-0.06

edn

-0.06

(f

-0.06

PLAIN

-0.06

pci

-0.06

 worlds

-0.06

POSITIVE LOGITS

 hấp

0.07

 сна

0.06

.WebControls

0.06

 rearr

0.06

&W

0.06

 след

0.06

 forensic

0.06

 часто

0.06

.epam

0.06

组织

0.06

Activations Density 0.004%

.

equations and mathematical expressions.

The neuron fires on floating‐point numeric literals (decimal numbers).

No Comments

No Known Activations