INDEX

Explanations

references to the consequences of duplicate content and related comparisons or analogies

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

ATHER

-0.15

aven

-0.15

ops

-0.14

Ã³r

-0.14

SEL

-0.14

ä¸¸

-0.14

Luz

-0.13

ronic

-0.13

 NotImplemented

-0.13

agged

-0.13

POSITIVE LOGITS

 analogy

0.18

ringe

0.17

alan

0.15

ompiler

0.14

ÑĪÑĮ

0.13

ÏĦÏģ

0.13

RIPT

0.13

ÏīÎ¼Î±

0.13

ÐłÐĲ

0.13

Tw

0.13

Activations Density 0.058%

references to the consequences of duplicate content and related comparisons or analogies

No Comments

No Known Activations