INDEX

Explanations

Start of sentences

np_max-act · gemini-2.0-flash

This neuron fires on the very first word of a new sentence (i.e. it detects sentence-initial tokens).

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DED

-0.06

otron

-0.06

 MQTT

-0.06

那

-0.06

温度

-0.06

DBC

-0.06

SUV

-0.06

Gtk

-0.06

답

-0.06

endet

-0.05

POSITIVE LOGITS

î

0.07

/");↵

0.07

Ο

0.07

lij

0.07

 رشته

0.07

0.06

)';↵

0.06

 chast

0.06

 relic

0.06

ccb

0.06

Activations Density 0.129%

Start of sentences

This neuron fires on the very first word of a new sentence (i.e. it detects sentence-initial tokens).

No Comments

No Known Activations

Start of sentences

This neuron fires on the very first word of a new sentence (i.e. it detects sentence-initial tokens).

No Comments

No Known Activations