INDEX

Explanations

occurrences of numerical values and formatting specific to financial or statistical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

uli

-0.16

Ã©nÃ©

-0.16

æĲ

-0.15

Ø§Ø²

-0.15

 broken

-0.14

 Î´Î·Î¼Î¿

-0.14

.Drop

-0.14

ewan

-0.14

engo

-0.14

 dropped

-0.14

POSITIVE LOGITS

ABCDE

0.19

aan

0.16

uga

0.15

 EntityState

0.15

Ħĸ

0.15

Ð°Ð»Ðµ

0.14

ROUGH

0.14

ovÃŃ

0.14

tring

0.14

ORITY

0.14

Activations Density 0.102%

occurrences of numerical values and formatting specific to financial or statistical contexts

No Comments

No Known Activations