INDEX

Explanations

references to technical or operational terms related to systems or processes

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

 unlike

-0.15

bip

-0.15

è±Ĩ

-0.14

Bil

-0.14

isle

-0.13

Î¼ÎµÎ½

-0.13

RESH

-0.13

bil

-0.13

-0.12

ÐµÑĢÐ¶

-0.12

POSITIVE LOGITS

ached

0.15

WithIdentifier

0.14

maz

0.14

(æĹ¥

0.14

abbo

0.14

imary

0.13

á»§ng

0.13

 èĩ

0.13

ruba

0.13

ÑģÐ¸Ð¼

0.13

Activations Density 0.459%

references to technical or operational terms related to systems or processes

No Comments

No Known Activations