INDEX

Explanations

technical jargon and phrases related to computer programming and troubleshooting

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

ä¸ĸç´Ģ

-0.15

_UNUSED

-0.15

 Uncategorized

-0.15

mpz

-0.15

emain

-0.14

(!!

-0.14

inka

-0.14

olean

-0.14

..↵↵↵↵

-0.13

tÃ¼r

-0.13

POSITIVE LOGITS

 https

0.15

 your

0.15

 yourself

0.15

 Forum

0.14

 exact

0.14

PM

0.13

.Localization

0.13

you

0.13

 quickest

0.13

Activations Density 0.149%

technical jargon and phrases related to computer programming and troubleshooting

No Comments

No Known Activations