INDEX

Explanations

mathematical notation and formatting in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Moh

-0.16

afc

-0.15

Ram

-0.14

sei

-0.14

icts

-0.14

 bere

-0.13

 Â»

-0.13

?url

-0.13

ichtet

-0.13

 under

-0.13

POSITIVE LOGITS

end

0.42

rais

0.28

label

0.21

eea

0.21

èģ

0.19

endcode

0.19

rbrakk

0.18

endphp

0.18

endregion

0.18

#endif

0.17

Activations Density 0.072%

mathematical notation and formatting in equations

No Comments

No Known Activations