INDEX

Explanations

class

np_max-act · gemini-2.0-flash

This neuron detects C++ template parameter declarations, i.e. occurrences of “<class” or “<typename” in template headers.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TR

-0.07

ırken

-0.07

初

-0.07

 Anton

-0.07

 đang

-0.06

 hãy

-0.06

 Ну

-0.06

ütün

-0.06

А

-0.06

�

-0.06

POSITIVE LOGITS

 exist

0.07

 beside

0.07

폐

0.06

cef

0.06

 Cross

0.06

�

0.06

Resources

0.06

 cardiovascular

0.06

 Chemical

0.06

 cấu

0.06

Activations Density 0.002%

class

This neuron detects C++ template parameter declarations, i.e. occurrences of “<class” or “<typename” in template headers.

No Comments

No Known Activations