INDEX

Explanations

cursor

np_max-act · gemini-2.0-flash

The neuron detects references to creating or using a database cursor (e.g. “cursor = …”, `.cursor()`, `.execute()`, `.fetchall()`).

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

ainer

-0.07

parency

-0.07

astery

-0.07

Brian

-0.07

Life

-0.07

ые

-0.06

 caps

-0.06

 país

-0.06

loads

-0.06

opleft

-0.06

POSITIVE LOGITS

_same

0.07

 sola

0.06

 заболева

0.06

 veriler

0.06

 مست

0.06

(ob

0.06

्वर

0.06

 бла

0.06

/sbin

0.06

 हट

0.06

Activations Density 0.003%

cursor

The neuron detects references to creating or using a database cursor (e.g. “cursor = …”, `.cursor()`, `.execute()`, `.fetchall()`).

No Comments

No Known Activations

cursor

The neuron detects references to creating or using a database cursor (e.g. “cursor = …”, `.cursor()`, `.execute()`, `.fetchall()`).

No Comments

No Known Activations