INDEX

Explanations

Medical studies abbreviations

np_max-act · gemini-2.0-flash

This neuron fires on medical condition abbreviations (e.g. RA, MDD, SLE, PsA, etc.).

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

 fetus

-0.07

 courageous

-0.06

"#

-0.06

arcer

-0.06

icago

-0.06

 ------------------------------------------------

-0.06

Brightness

-0.06

Center

-0.06

 Kür

-0.06

Postal

-0.06

POSITIVE LOGITS

 Boeh

0.07

ph

0.06

pping

0.06

_LITERAL

0.06

 Exact

0.06

 retard

0.06

venth

0.06

 พฤศจ

0.06

/win

0.06

bsd

0.06

Activations Density 0.040%

Medical studies abbreviations

This neuron fires on medical condition abbreviations (e.g. RA, MDD, SLE, PsA, etc.).

No Comments

No Known Activations