INDEX

Explanations

with

np_max-act · gemini-2.0-flash

This neuron responds to key subjects and linking verbs in clinical or scientific sentences—e.g. nouns like “patient,” “woman,” “chick,” “neutrophil” and verbs such as “was,” “can,” “has,” and “be” that introduce or describe the main subject.

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

gage

-0.06

shed

-0.06

Page

-0.06

 management

-0.06

obj

-0.06

 listings

-0.06

 inviting

-0.06

 stock

-0.06

 fibr

-0.06

POSITIVE LOGITS

.setName

0.07

 superheroes

0.07

LOT

0.06

SG

0.06

하며

0.06

 anche

0.06

#(

0.06

/social

0.06

근

0.06

 Katrina

0.06

Activations Density 0.220%

with

This neuron responds to key subjects and linking verbs in clinical or scientific sentences—e.g. nouns like “patient,” “woman,” “chick,” “neutrophil” and verbs such as “was,” “can,” “has,” and “be” that introduce or describe the main subject.

No Comments

No Known Activations