INDEX

Explanations

references to programming functions and objects related to data handling and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

andas

-0.18

ãĥ¼

-0.15

amaz

-0.14

 profit

-0.14

 Neptune

-0.14

rar

-0.14

ennon

-0.13

 Booker

-0.13

nbsp

-0.13

ible

-0.13

POSITIVE LOGITS

amilia

0.16

íĦ¸

0.15

okers

0.15

tml

0.15

/www

0.14

anko

0.14

 DÃ¼n

0.14

opia

0.14

ourcem

0.14

_LS

0.14

Activations Density 0.054%

references to programming functions and objects related to data handling and manipulation

No Comments

No Known Activations