INDEX

Explanations

references to various sources, figures, and citations

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

 hundred

-0.27

 Hundred

-0.26

-0.23

 Cent

-0.23

-0.21

 cent

-0.21

POSITIVE LOGITS

ten

0.18

 twelve

0.18

0.17

 nine

0.17

 thirteen

0.17

0.16

Î»Î¹ÎºÎ¬

0.15

Activations Density 0.174%

references to various sources, figures, and citations

No Comments

No Known Activations