INDEX

Explanations

punctuation marks and symbols in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 therefore

-0.33

 Therefore

-0.29

Therefore

-0.28

 hence

-0.26

æīĢä»¥

-0.24

 donc

-0.23

 consequently

-0.23

 Hence

-0.22

ï¼ĮæīĢä»¥

-0.22

 wiÄĻc

-0.21

POSITIVE LOGITS

Alternatively

0.34

 Alternatively

0.32

 alternatively

0.27

Or

0.26

 otherwise

0.26

or

0.24

altern

0.24

 Otherwise

0.24

 Altern

0.23

.Or

0.23

Activations Density 0.146%

punctuation marks and symbols in text

No Comments

No Known Activations