INDEX

Explanations

mathematical symbols and operations related to integrals 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ey

-0.17

oras

-0.15

ëħĢ

-0.14

otate

-0.14

 cÃ¡

-0.14

 obstruct

-0.13

fuse

-0.13

uto

-0.13

Ã

-0.13

Ð¾ÑĢÐ¾Ð´

-0.13

POSITIVE LOGITS

.Commit

0.17

stral

0.16

Cad

0.15

atchet

0.15

ãİ

0.15

ãĤ¤

0.14

erk

0.14

oins

0.14

inho

0.14

adece

0.14

Activations Density 0.038%

mathematical symbols and operations related to integrals and limits

No Comments

No Known Activations