INDEX

Explanations

programming-related header files and preprocessor directives

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

iente

-0.17

ente

-0.16

igham

-0.15

iba

-0.14

en

-0.14

Ãªn

-0.14

parallel

-0.13

ents

-0.13

icens

-0.13

 scenario

-0.13

POSITIVE LOGITS

Å¾e

0.15

 Ð¸Ð¼Ð¿

0.15

Ä°L

0.15

Ä°S

0.15

 ìĹĦ

0.15

ÑĪÐµÐ²

0.14

ÃŃses

0.14

datagrid

0.14

 Builders

0.14

Ã©tique

0.13

Activations Density 0.001%

programming-related header files and preprocessor directives

No Comments

No Known Activations