INDEX

Explanations

mathematical terms and concepts related to category theory

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/Error

-0.18

 Dude

-0.17

 Conc

-0.16

lia

-0.16

Sak

-0.15

-0.14

EEE

-0.14

 closure

-0.14

 Mild

-0.14

POSITIVE LOGITS

invert

0.17

sur

0.16

ibold

0.16

ãĥ

0.15

ORK

0.15

 Transit

0.15

-cover

0.15

 Mayer

0.15

eto

0.14

Ð¾Ð¼Ð°

0.14

Activations Density 0.349%

mathematical terms and concepts related to category theory

No Comments

No Known Activations