INDEX

Explanations

programming constructs and patterns commonly used in code, particularly related to data structures and processing functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ï¼īãģ¯

-0.18

'];?>

-0.16

avana

-0.14

');?>

-0.14

']",

-0.14

})",

-0.14

 (...

-0.14

isEqualTo

-0.14

sizei

-0.14

ĥģ

-0.14

POSITIVE LOGITS

”

0.25

[]"

0.20

()

0.20

]()

0.19

0.18

\)

0.18

()"

0.17

="/"

0.17

Activations Density 0.187%

programming constructs and patterns commonly used in code, particularly related to data structures and processing functions

No Comments

No Known Activations