INDEX

Explanations

detail

np_max-act · gemini-2.0-flash

This neuron fires on C++ code constructs—especially template‐ and namespace‐related declarations in header files.

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

 يون

-0.07

onsense

-0.07

.skills

-0.06

HEL

-0.06

cool

-0.06

Rick

-0.06

got

-0.06

.DataAnnotations

-0.06

PageRoute

-0.06

FORM

-0.06

POSITIVE LOGITS

 phía

0.06

�

0.06

Lab

0.06

ाई

0.06

піон

0.06

 dari

0.06

 earns

0.06

าพ

0.06

leans

0.06

 تاريخ

0.06

Activations Density 0.002%

detail

This neuron fires on C++ code constructs—especially template‐ and namespace‐related declarations in header files.

No Comments

No Known Activations

detail

This neuron fires on C++ code constructs—especially template‐ and namespace‐related declarations in header files.

No Comments

No Known Activations