INDEX

Explanations

mathematical notations and expressions related to functions and limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

iyet

-0.15

ãĥ¼ãĤ

-0.14

<=>

-0.14

 khá»ıi

-0.14

cplusplus

-0.14

mÃ¼r

-0.14

blocking

-0.14

antine

-0.13

ngth

-0.13

Ker

-0.13

POSITIVE LOGITS

Obl

0.16

å¤©

0.14

han

0.14

uda

0.14

mo

0.14

Tor

0.14

tre

0.13

tor

0.13

 Darkness

0.13

jos

0.13

Activations Density 0.064%

mathematical notations and expressions related to functions and limits

No Comments

No Known Activations