INDEX

Explanations

code

np_max-act · gemini-2.0-flash

This neuron fires on code that accesses fragment arguments (e.g. calls to arguments!!.getInt(…) and related tokens around retrieving passed-in parameters).

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

rup

-0.06

 Places

-0.06

_query

-0.06

AH

-0.06

ARGER

-0.06

YSTICK

-0.06

:''

-0.06

 Kush

-0.06

.jdbc

-0.06

 frustrated

-0.06

POSITIVE LOGITS

 брос

0.07

別

0.07

 Adams

0.06

 ******************************************************************************/↵

0.06

 Efficiency

0.06

品

0.06

]),↵

0.06

空

0.06

))));↵

0.06

drink

0.06

Activations Density 0.027%

code

This neuron fires on code that accesses fragment arguments (e.g. calls to arguments!!.getInt(…) and related tokens around retrieving passed-in parameters).

No Comments

No Known Activations