INDEX

Explanations

details related to event logistics and refreshments

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

 mornings

-0.16

 Spoon

-0.16

 weekends

-0.15

.Pow

-0.15

qua

-0.14

 nested

-0.14

 Cooking

-0.14

 Weekend

-0.14

aux

-0.14

ç«¹

-0.14

POSITIVE LOGITS

 refresh

0.47

refresh

0.35

 Refresh

0.34

Refresh

0.33

 snacks

0.31

_refresh

0.28

 drinks

0.27

-refresh

0.27

.refresh

0.25

_REFRESH

0.25

Activations Density 0.177%

details related to event logistics and refreshments

No Comments

No Known Activations

details related to event logistics and refreshments

No Comments

No Known Activations