INDEX

Explanations

code snippets related to programming tasks and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 mouth

-0.16

ikip

-0.16

Ð°Ð±Ð»Ð¸ÑĨ

-0.14

arrass

-0.14

utton

-0.14

Kra

-0.14

iber

-0.14

wealth

-0.14

-append

-0.13

qual

-0.13

POSITIVE LOGITS

 //!<

0.16

ALS

0.15

ABL

0.15

frei

0.14

uis

0.14

å«

0.14

als

0.14

iliar

0.14

ARA

0.14

/MIT

0.13

Activations Density 0.013%

code snippets related to programming tasks and functions

No Comments

No Known Activations