INDEX

Explanations

references to locations and institutions

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

inho

-0.15

ãĤ°ãĥ©

-0.15

.GetLength

-0.14

bsub

-0.14

ÅĻÃŃ

-0.14

 Croat

-0.13

 Mund

-0.13

Ð¾Ð»ÑĮÐºÑĥ

-0.13

ino

-0.13

zek

-0.13

POSITIVE LOGITS

meer

0.15

 à¸Ľà¸£à¸°à¹Ģà¸Ĺà¸¨

0.15

 Yard

0.14

WithType

0.14

rous

0.14

tron

0.14

ugo

0.14

USA

0.14

con

0.14

inned

0.14

Activations Density 0.179%

references to locations and institutions

No Comments

No Known Activations