INDEX

Explanations

research methods

np_max-act · gemini-2.0-flash

The neuron detects document section or subsection headings (e.g. “Methods,” “Setting,” “Study design and patient inclusion,” “Participants”).

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

mrt

-0.07

.Euler

-0.07

ded

-0.06

_SERVER

-0.06

NRF

-0.06

.Extension

-0.06

 тв

-0.06

Ｙ

-0.06

_CLK

-0.06

 طرف

-0.06

POSITIVE LOGITS

 dispose

0.07

dis

0.07

bk

0.07

rawl

0.07

Patch

0.06

idelity

0.06

 disabled

0.06

 beam

0.06

.dumps

0.06

 الأد

0.06

Activations Density 0.002%

research methods

The neuron detects document section or subsection headings (e.g. “Methods,” “Setting,” “Study design and patient inclusion,” “Participants”).

No Comments

No Known Activations