INDEX

Explanations

applications and access

np_max-act · gemini-2.0-flash

The neuron flags terms referring to provider credentialing or enrollment procedures (e.g., credentialing, enrollment, onboarding, account opening).

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

 Excellence

-0.07

 cara

-0.06

MPH

-0.06

Row

-0.06

 Brendan

-0.06

_PC

-0.06

-schema

-0.06

mw

-0.06

 café

-0.06

 pentru

-0.06

POSITIVE LOGITS

+",

0.07

OptionsItemSelected

0.06

числ

0.06

	throws

0.06

Fant

0.06

#__

0.06

 heeft

0.06

停

0.06

 evolves

0.06

extAlignment

0.06

Activations Density 0.032%

applications and access

The neuron flags terms referring to provider credentialing or enrollment procedures (e.g., credentialing, enrollment, onboarding, account opening).

No Comments

No Known Activations

applications and access

The neuron flags terms referring to provider credentialing or enrollment procedures (e.g., credentialing, enrollment, onboarding, account opening).

No Comments

No Known Activations