INDEX

Explanations

mathematical notations and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

åĪĬ

-0.18

ConnectionString

-0.17

ÐµÐ»Ð¸Ñĩ

-0.14

åľ³

-0.14

dsn

-0.14

æľĽ

-0.14

æº

-0.14

 ÅĻ

-0.13

.ConnectionString

-0.13

ports

-0.13

POSITIVE LOGITS

0.14

ÑģÑĮÐ¾Ð³Ð¾

0.14

ubs

0.14

TOD

0.13

eil

0.13

 Gilles

0.13

ovol

0.13

ph

0.13

0.12

tr

0.12

Activations Density 0.158%

mathematical notations and expressions

No Comments

No Known Activations