INDEX

Explanations

code that includes function definitions and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Formatted

-0.15

ving

-0.15

que

-0.14

ëĶĶìĭľ

-0.13

 diplom

-0.13

Descriptors

-0.13

uppercase

-0.13

ova

-0.13

BadRequest

-0.13

 ëĦ¤ìĿ´íĬ¸

-0.13

POSITIVE LOGITS

 name

0.16

 Namen

0.15

istrovstvÃŃ

0.14

itag

0.14

Bonjour

0.13

ì¹ł

0.13

ÐµÐ»Ð¸Ñĩ

0.13

 Ð¸ÑģÑĤÐ¾Ñĩ

0.13

à¸Ĭà¸Ļ

0.13

-LAST

0.12

Activations Density 1.594%

code that includes function definitions and parameters

No Comments

No Known Activations