INDEX

Explanations

semicolon

np_max-act · gemini-2.0-flash

The neuron flags usages of general-purpose utility class identifiers (e.g. “Utils,” “Strings,” “Pair,” etc.).

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

 Chart

-0.07

 구글

-0.07

annotate

-0.07

 Guidance

-0.06

 ẩn

-0.06

GridView

-0.06

 semiclassical

-0.06

 riots

-0.06

jad

-0.06

POSITIVE LOGITS

스크

0.06

 adet

0.06

дж

0.06

ΙΟ

0.06

тє

0.06

 enhances

0.06

픈

0.06

 computers

0.06

 "),↵

0.06

ğim

0.06

Activations Density 0.005%

semicolon

The neuron flags usages of general-purpose utility class identifiers (e.g. “Utils,” “Strings,” “Pair,” etc.).

No Comments

No Known Activations