INDEX

Explanations

visibility

np_max-act · gemini-2.0-flash

The neuron flags when the text talks about user-interface or configuration “options” (menu items, settings, or commands) being shown, missing, or appearing.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

technical issues and guidance related to software development.

oai_token-act-pair · gpt-4o-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

हर

-0.06

aremos

-0.06

 ulož

-0.06

ontvangst

-0.06

etermin

-0.06

arf

-0.05

цию

-0.05

 ngành

-0.05

-D

-0.05

POSITIVE LOGITS

 образ

0.07

 تقد

0.07

 marching

0.07

 مکان

0.07

 пла

0.07

 صلى

0.07

RHS

0.07

 relocated

0.07

中学

0.07

 北京

0.06

Activations Density 0.029%

visibility

The neuron flags when the text talks about user-interface or configuration “options” (menu items, settings, or commands) being shown, missing, or appearing.

technical issues and guidance related to software development.

No Comments

No Known Activations