INDEX

Explanations

transition

np_max-act · gemini-2.0-flash

This neuron primarily activates on occurrences of the verb “emerge” (and its inflected forms).

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

Again

-0.07

Rh

-0.06

ZD

-0.06

"${

-0.06

 subscriber

-0.06

yst

-0.06

erto

-0.06

 villain

-0.06

eye

-0.06

�

-0.06

POSITIVE LOGITS

_AHB

0.07

 ViewPager

0.07

부터

0.07

vfs

0.07

_ipc

0.07

tensorflow

0.06

 uphol

0.06

haar

0.06

 butcher

0.06

_UNIX

0.06

Activations Density 0.040%

transition

This neuron primarily activates on occurrences of the verb “emerge” (and its inflected forms).

No Comments

No Known Activations