INDEX

Explanations

medical database searches

np_max-act · gemini-2.0-flash

This neuron activates on terms and symbols used in systematic‐review literature search queries—i.e. database search keywords, MeSH terms, and Boolean operators.

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

の子

-0.07

avir

-0.06

>Password

-0.06

eday

-0.06

 мак

-0.06

を開

-0.06

沿

-0.06

gui

-0.06

 अध

-0.06

 feudal

-0.06

POSITIVE LOGITS

webElementXpaths

0.07

.'↵↵

0.07

_URL

0.07

?"↵↵

0.06

Farm

0.06

Inventory

0.06

iere

0.06

.fa

0.06

!(↵

0.06

 çeşitli

0.06

Activations Density 0.004%

medical database searches

This neuron activates on terms and symbols used in systematic‐review literature search queries—i.e. database search keywords, MeSH terms, and Boolean operators.

No Comments

No Known Activations