INDEX

Explanations

programming-related terminology and functions, specifically in the context of configuration and settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Dich

-0.14

ilestone

-0.14

abcdefghijkl

-0.14

Î»ÎµÎº

-0.13

 ê·¸ëłĩ

-0.13

jiÅ¡Å¥

-0.12

-turned

-0.12

yclopedia

-0.12

erce

-0.12

Å¼y

-0.12

POSITIVE LOGITS

/high

0.17

nar

0.13

Ð¾Ð½Ð°Ð»ÑĮ

0.13

.getSharedPreferences

0.12

 nghá»ģ

0.12

ÑģÐ¾ÑĤ

0.12

 Â«

0.12

nar

0.12

chers

0.12

icone

0.11

Activations Density 0.914%

programming-related terminology and functions, specifically in the context of configuration and settings

No Comments

No Known Activations