INDEX

Explanations

MS

np_max-act · gemini-2.0-flash

The neuron activates on tokens referring to mass-spectrometry methods (e.g. “MS,” “spectrom,” “LC-MS/MS,” “UPLC-MS/MS,” etc.).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

INavigationController

-0.07

Entity

-0.06

/projects

-0.06

많

-0.06

 statutes

-0.06

ันด

-0.06

_attrs

-0.06

var

-0.06

POSITIVE LOGITS

bons

0.06

 reactionary

0.06

寶

0.06

ASA

0.06

lomou

0.06

NSS

0.06

riters

0.06

anos

0.06

ott

0.06

 loses

0.06

Activations Density 0.003%

MS

The neuron activates on tokens referring to mass-spectrometry methods (e.g. “MS,” “spectrom,” “LC-MS/MS,” “UPLC-MS/MS,” etc.).

No Comments

No Known Activations