INDEX

Explanations

word origins

np_max-act · gemini-2.0-flash

This neuron detects when a text is breaking a word into its component roots or morphemes—i.e. marking out parts of a word during an etymological explanation.

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

.Close

-0.07

 sound

-0.06

ecycle

-0.06

textView

-0.06

 realized

-0.06

opencv

-0.06

JD

-0.06

 posto

-0.06

 impressed

-0.06

μένων

-0.06

POSITIVE LOGITS

 سپتامبر

0.07

 flirt

0.06

 Ваш

0.06

оді

0.06

�

0.06

@nate

0.06

ród

0.06

파

0.06

 fabs

0.06

パ

0.06

Activations Density 0.029%

word origins

This neuron detects when a text is breaking a word into its component roots or morphemes—i.e. marking out parts of a word during an etymological explanation.

No Comments

No Known Activations