INDEX

Explanations

messages

np_max-act · gemini-2.0-flash

The neuron activates on instances of the word “voicemail.”

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

findOne

-0.07

Programming

-0.07

()]↵

-0.06

 precision

-0.06

getId

-0.06

_intersection

-0.06

 coeffs

-0.06

 projectId

-0.06

POSITIVE LOGITS

icemail

0.08

 lear

0.06

_HEIGHT

0.06

 ответ

0.06

чи

0.06

olders

0.06

 sogar

0.06

mirror

0.06

 Puppy

0.06

اط

0.06

Activations Density 0.007%

messages

The neuron activates on instances of the word “voicemail.”

No Comments

No Known Activations