INDEX

Explanations

.config

np_max-act · gemini-2.0-flash

The neuron activates on lines where the Flask app’s configuration is being accessed or set (i.e. `app.config[...]`).

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

ونه

-0.07

áhnout

-0.06

_sw

-0.06

 reckless

-0.06

_adapter

-0.06

 landlords

-0.06

 lender

-0.06

 seminal

-0.06

Prepare

-0.06

言う

-0.05

POSITIVE LOGITS

_Details

0.07

 diets

0.07

 pollut

0.07

ERP

0.07

))?

0.07

 domaine

0.07

Daily

0.07

.componentInstance

0.07

implicitly

0.06

 الأد

0.06

Activations Density 0.000%

.config

The neuron activates on lines where the Flask app’s configuration is being accessed or set (i.e. `app.config[...]`).

No Comments

No Known Activations