INDEX

Explanations

numerical or quantifiable references, particularly in academic or statistical contexts

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

STRU

-0.15

oldt

-0.15

ushima

-0.15

ı

-0.14

ÙģØ´

-0.14

andan

-0.14

iao

-0.14

achen

-0.13

ãĥ©ãĤ¹

-0.13

¾

-0.13

POSITIVE LOGITS

adu

0.18

.WinForms

0.17

pic

0.15

ulum

0.15

pic

0.14

 Omega

0.14

æ³Ĭ

0.14

ga

0.14

Activations Density 0.001%

numerical or quantifiable references, particularly in academic or statistical contexts

No Comments

No Known Activations