INDEX

Explanations

Code casting

np_max-act · gemini-2.0-flash

The neuron fires on tokens related to explicit type‐conversion or “cast” operations in code.

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

α

-0.07

erti

-0.07

_recipe

-0.07

delta

-0.06

uran

-0.06

_macro

-0.06

 goTo

-0.06

_feed

-0.06

 tả

-0.06

πε

-0.06

POSITIVE LOGITS

 PORT

0.07

orgetown

0.06

�

0.06

 Formats

0.06

μένου

0.06

 شكل

0.06

.spawn

0.06

-con

0.06

 DISCLAIMS

0.06

 pourquoi

0.06

Activations Density 0.021%

Code casting

The neuron fires on tokens related to explicit type‐conversion or “cast” operations in code.

No Comments

No Known Activations

Code casting

The neuron fires on tokens related to explicit type‐conversion or “cast” operations in code.

No Comments

No Known Activations