INDEX

Explanations

phrases indicating importance or significance related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 even

-0.18

ãģķãĤī

-0.17

çĶļèĩ³

-0.17

 tháºŃm

-0.16

even

-0.16

 although

-0.16

 ademÃ¡s

-0.15

 aside

-0.15

 only

-0.15

 ONLY

-0.15

POSITIVE LOGITS

 nevertheless

0.53

 nonetheless

0.52

Nevertheless

0.46

 Nonetheless

0.39

 Nevertheless

0.38

 still

0.28

è¿ĺæĺ¯

0.28

åį´

0.28

 Still

0.27

Still

0.26

Activations Density 0.584%

phrases indicating importance or significance related to various topics

No Comments

No Known Activations

phrases indicating importance or significance related to various topics

No Comments

No Known Activations