INDEX

Explanations

code snippets

np_max-act · gemini-2.0-flash

The neuron detects mentions of installing or importing required libraries (e.g. “install,” library names, “pip,” “import,” “the required libraries”).

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

Hidden

-0.07

Disney

-0.07

 psycopg

-0.07

 Spend

-0.07

_accounts

-0.06

Türk

-0.06

 derivatives

-0.06

backend

-0.06

swap

-0.06

],"

-0.06

POSITIVE LOGITS

ические

0.07

 stemming

0.06

cj

0.06

 감사

0.06

eeee

0.06

.Sql

0.06

 excessively

0.06

 CORPOR

0.06

━━━━

0.06

(op

0.06

Activations Density 0.024%

code snippets

The neuron detects mentions of installing or importing required libraries (e.g. “install,” library names, “pip,” “import,” “the required libraries”).

No Comments

No Known Activations