INDEX

Explanations

programming-related keywords and events, particularly associated with user interface interactions and AJAX functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

dio

-0.18

Ð¾Ð¿Ð¾Ð»

-0.18

ÑģÑĤÐ¸

-0.17

åªĴ

-0.15

interopRequire

-0.15

sein

-0.15

rna

-0.15

edor

-0.14

owie

-0.14

Verse

-0.14

POSITIVE LOGITS

 Garcia

0.15

ernal

0.15

Bou

0.14

ë§Īëĭ¤

0.14

illes

0.14

Ã³st

0.13

ges

0.13

:^(

0.13

ides

0.13

Activations Density 0.053%

programming-related keywords and events, particularly associated with user interface interactions and AJAX functions

No Comments

No Known Activations