INDEX

Explanations

mathematical symbols and operators involved 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ing

-0.20

 Ð¶Ðµ

-0.15

cess

-0.14

ress

-0.14

Ð½ÑĥÐ²

-0.14

anou

-0.14

NOWLED

-0.14

ãĤīãģĽ

-0.13

gross

-0.13

isch

-0.13

POSITIVE LOGITS

.LayoutStyle

0.17

atas

0.15

 Stam

0.15

VEC

0.14

 Bauer

0.14

fieldname

0.14

 subt

0.13

ugins

0.13

nda

0.13

ÑıÑĤÐµÐ»ÑĮ

0.13

Activations Density 0.039%

mathematical symbols and operators involved in equations

No Comments

No Known Activations