INDEX

Explanations

is

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the word “sepsis,” detecting mentions of that medical condition.

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

 оп

-0.06

 gathering

-0.06

ört

-0.06

 compens

-0.06

opup

-0.06

 гор

-0.06

/state

-0.06

icits

-0.06

 suited

-0.06

 Fine

-0.06

POSITIVE LOGITS

 začal

0.07

nw

0.07

 isteyen

0.06

 avere

0.06

?,?,?,?,

0.06

################

0.06

 trainable

0.06

 развития

0.06

[indexPath

0.06

 nicknamed

0.06

Activations Density 0.116%

is

This neuron activates on occurrences of the word “sepsis,” detecting mentions of that medical condition.

No Comments

No Known Activations

is

This neuron activates on occurrences of the word “sepsis,” detecting mentions of that medical condition.

No Comments

No Known Activations