INDEX

Explanations

references to influential people or entities in various contexts

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

ande

-0.15

andas

-0.15

oom

-0.14

ret

-0.14

lio

-0.14

hetto

-0.13

 mouth

-0.13

 hide

-0.12

apg

-0.12

ufs

-0.12

POSITIVE LOGITS

zen

0.16

æĤ

0.15

UnitTest

0.14

achen

0.14

.SuspendLayout

0.14

onet

0.13

Ð¾ÑģÐ»Ð°Ð²

0.13

Ã³c

0.13

inth

0.13

zan

0.13

Activations Density 0.105%

references to influential people or entities in various contexts

No Comments

No Known Activations