INDEX

Explanations

arthritis

np_max-act · gemini-2.0-flash

the neuron responds to mentions of the word “arthritis.”

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

Screenshot

-0.07

Cel

-0.06

 hood

-0.06

_arguments

-0.06

-pocket

-0.06

Pipe

-0.06

 Lanc

-0.06

 bonding

-0.06

 encountered

-0.06

POSITIVE LOGITS

 arthritis

0.15

thritis

0.10

-settings

0.08

 Garrett

0.07

adjust

0.07

MaxY

0.07

qli

0.07

�

0.07

 Druid

0.07

恒

0.07

Activations Density 0.002%

arthritis

the neuron responds to mentions of the word “arthritis.”

No Comments

No Known Activations