INDEX

Explanations

mathematical symbols and their usage in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

.getOwnProperty

-0.16

legate

-0.16

ä»ķ

-0.15

oje

-0.15

ulty

-0.14

_:*

-0.14

bÃŃr

-0.14

rieve

-0.14

\">↵

-0.14

abbo

-0.14

POSITIVE LOGITS

0.35

 &↵

0.23

&&

0.22

}&

0.21

"&

0.19

'&

0.19

&)

0.19

&,

0.19

&_

0.18

Activations Density 0.030%

mathematical symbols and their usage in equations

No Comments

No Known Activations