INDEX

Explanations

programming terminology related to structure and organization

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

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

Pig

-0.16

 Abraham

-0.16

 Kerala

-0.15

ĭ

-0.15

isu

-0.15

irut

-0.15

 Lebanese

-0.14

shortcode

-0.14

YY

-0.14

 LIABILITY

-0.14

POSITIVE LOGITS

.mozilla

0.27

 mozilla

0.23

 Mozilla

0.23

 Liverpool

0.23

 Firefox

0.22

moz

0.21

ozilla

0.20

Liverpool

0.20

mozilla

0.18

 firefox

0.18

Activations Density 0.064%

programming terminology related to structure and organization

No Comments

No Known Activations