INDEX

Explanations

Repeated token

np_max-act · gemini-2.0-flash

This neuron detects document section separators or divider lines, such as sequences of dashes or equals, marking section headings.

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

iversite

-0.08

 taşın

-0.07

getMock

-0.07

Mul

-0.07

헤

-0.07

 manifold

-0.07

Так

-0.06

 مول

-0.06

mint

-0.06

申

-0.06

POSITIVE LOGITS

contest

0.06

呈

0.06

ج

0.06

 Ramp

0.06

がい

0.06

RGB

0.06

>{!!

0.06

.getContext

0.06

 indoor

0.06

lv

0.06

Activations Density 0.001%

Repeated token

This neuron detects document section separators or divider lines, such as sequences of dashes or equals, marking section headings.

No Comments

No Known Activations