INDEX

Explanations

technical terms and boolean values in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

()",

-0.20

()',

-0.18

{}",

-0.18

?',

-0.18

()"↵

-0.18

 {}",

-0.17

">'↵

-0.17

()č↵

-0.17

":"","

-0.17

'č↵

-0.17

POSITIVE LOGITS

,↵

0.39

\",↵

0.26

",↵

0.23

?,↵

0.23

_,↵

0.23

__,↵

0.23

.,↵

0.22

ï¼Į↵

0.22

 *,↵

0.21

[],↵

0.21

Activations Density 0.061%

technical terms and boolean values in a programming context

No Comments

No Known Activations