INDEX

Explanations

technical terms and jargon related to wiring and networking

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

atas

-0.16

 èĲ¬

-0.15

ÑĨÐ¾Ð²

-0.15

vinces

-0.15

uplic

-0.15

otal

-0.15

.modules

-0.15

toa

-0.14

 Elsa

-0.14

 Bolt

-0.14

POSITIVE LOGITS

ngr

0.17

 Category

0.15

 Struct

0.15

Lazy

0.14

Ŀ

0.14

 GÃ¼r

0.14

agg

0.14

Structured

0.14

PLEX

0.14

orne

0.14

Activations Density 0.345%

technical terms and jargon related to wiring and networking

No Comments

No Known Activations