INDEX

Explanations

StringIO

np_max-act · gemini-2.0-flash

The main thing this neuron picks up on is mentions of in-memory file-like buffer objects (e.g. StringIO or BytesIO).

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

"P

-0.07

"M

-0.07

 layouts

-0.07

.java

-0.07

-bg

-0.07

MESS

-0.06

"W

-0.06

LEM

-0.06

 dětí

-0.06

 Enemies

-0.06

POSITIVE LOGITS

 predictive

0.07

 Закону

0.07

 Pessoa

0.07

.settings

0.07

ountain

0.06

 توجه

0.06

.isPlaying

0.06

契

0.06

Gle

0.06

 StringIO

0.06

Activations Density 0.002%

StringIO

The main thing this neuron picks up on is mentions of in-memory file-like buffer objects (e.g. StringIO or BytesIO).

No Comments

No Known Activations