INDEX

Explanations

tr

np_max-act · gemini-2.0-flash

This neuron activates on HTML table row tags (the “<tr>” elements).

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

 DataBase

-0.07

theast

-0.07

 locationManager

-0.07

contre

-0.07

ă

-0.06

 ارائه

-0.06

 trumpet

-0.06

packet

-0.06

enario

-0.06

ीएम

-0.06

POSITIVE LOGITS

{:.

0.06

.Primary

0.06

Roboto

0.06

 constituents

0.06

 ripping

0.06

ultureInfo

0.06

LLLL

0.06

histor

0.06

 Insp

0.06

심

0.06

Activations Density 0.003%

tr

This neuron activates on HTML table row tags (the “<tr>” elements).

No Comments

No Known Activations