INDEX

Explanations

(

np_max-act · gemini-2.0-flash

This neuron detects references to build‐system variables, specifically the “$(” prefix used for macro or property expansions.

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

Ric

-0.06

 mirrors

-0.06

 mariage

-0.06

Gender

-0.06

 player

-0.06

.Man

-0.06

 eher

-0.06

 nationalism

-0.06

_SCHED

-0.06

(Parser

-0.06

POSITIVE LOGITS

 obese

0.07

jsonData

0.07

 могла

0.06

让

0.06

解

0.06

φων

0.06

 unsuccessful

0.06

toThrow

0.06

 آن

0.06

ließ

0.06

Activations Density 0.001%

(

This neuron detects references to build‐system variables, specifically the “$(” prefix used for macro or property expansions.

No Comments

No Known Activations