INDEX

Explanations

details related to specific events, locations, and images associated with individuals or entities

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icol

-0.15

/libs

-0.15

æ¼ı

-0.14

<::

-0.14

amine

-0.14

 PROCUREMENT

-0.13

ModelIndex

-0.13

èĥĨ

-0.13

cest

-0.13

 Ticaret

-0.13

POSITIVE LOGITS

ody

0.15

Typ

0.14

 recent

0.14

æĪ´

0.14

 grinder

0.13

 Sidebar

0.13

olia

0.13

ang

0.13

ARGER

0.13

ÅĻÃŃd

0.13

Activations Density 0.034%

details related to specific events, locations, and images associated with individuals or entities

No Comments

No Known Activations