INDEX

Explanations

specific terms and phrases related to authorship and programming constructs in code documentation

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

æĦı

-0.17

rottle

-0.16

Scheme

-0.15

 scheme

-0.15

 Scheme

-0.14

ÐµÐ¶

-0.14

Ã³m

-0.14

ettle

-0.14

 organs

-0.14

CAF

-0.14

POSITIVE LOGITS

á»¥c

0.15

yh

0.15

ãģ«è¦ĭ

0.14

AFX

0.14

itur

0.14

kening

0.14

.tx

0.14

acher

0.14

 ^{Â°}

0.13

íĹ¤

0.13

Activations Density 0.006%

specific terms and phrases related to authorship and programming constructs in code documentation

No Comments

No Known Activations