INDEX

Explanations

code

np_max-act · gemini-2.0-flash

definitions and declarations related to structures and classes in programming.

oai_token-act-pair · gpt-4o-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

-weight

-0.07

 Response

-0.07

 Garner

-0.07

aghetti

-0.07

 cyclic

-0.07

olarity

-0.07

Allowed

-0.07

 monitors

-0.06

	base

-0.06

 furry

-0.06

POSITIVE LOGITS

@ResponseBody

0.07

habi

0.06

searchModel

0.06

SACTION

0.06

 서울특별시

0.06

 sind

0.06

TODO

0.06

 іншими

0.06

@implementation

0.06

 کشور

0.06

Activations Density 0.077%

code

definitions and declarations related to structures and classes in programming.

No Comments

No Known Activations