INDEX

Explanations

medical imaging

np_max-act · gemini-2.0-flash

This neuron detects mentions of specific imaging modalities (e.g. “microscopy images,” “ultrasound images”) in the text.

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

 götür

-0.06

"~/

-0.06

	layer

-0.06

Ruby

-0.06

wc

-0.06

adm

-0.06

¯

-0.06

 tors

-0.06

(>

-0.06

�

-0.06

POSITIVE LOGITS

レン

0.07

pais

0.07

cock

0.07

affer

0.07

Comm

0.06

 Interview

0.06

 Declaration

0.06

.O

0.06

 tradition

0.06

Concept

0.06

Activations Density 0.053%

medical imaging

This neuron detects mentions of specific imaging modalities (e.g. “microscopy images,” “ultrasound images”) in the text.

No Comments

No Known Activations