INDEX

Explanations

terms related to online education and professional development resources

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

èĬĻ

-0.17

aga

-0.16

rist

-0.16

rat

-0.16

lah

-0.15

ha

-0.15

rat

-0.15

bor

-0.15

xda

-0.14

 Engineer

-0.14

POSITIVE LOGITS

Sy

0.16

estar

0.15

Iso

0.15

ekl

0.15

.sy

0.15

 kims

0.15

ullan

0.15

 Shepard

0.14

koc

0.14

quals

0.14

Activations Density 0.176%

terms related to online education and professional development resources

No Comments

No Known Activations