INDEX

Explanations

m

np_max-act · gemini-2.0-flash

The neuron fires on short technical fragments or abbreviations—especially tokens like “Res,” “die,” “D,” and similar brief letter‐sequences that occur in chemical/material names.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

caps

-0.07

主

-0.07

York

-0.07

너

-0.06

붙

-0.06

IDTH

-0.06

-signed

-0.06

事

-0.06

-blue

-0.06

:{↵

-0.06

POSITIVE LOGITS

.ImageField

0.07

navbarSupportedContent

0.06

]↵↵↵↵

0.06

↵

0.06

出版社

0.06

 γλώ

0.06

 wasn

0.06

 ];
↵

0.06

 xứ

0.06

ug

0.06

Activations Density 0.197%

m

The neuron fires on short technical fragments or abbreviations—especially tokens like “Res,” “die,” “D,” and similar brief letter‐sequences that occur in chemical/material names.

No Comments

No Known Activations