INDEX

Explanations

metadata and descriptive elements in API documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

bos

-0.17

isd

-0.16

áº¥u

-0.15

omm

-0.15

eldon

-0.14

.ci

-0.14

ci

-0.14

Ð»Ñı

-0.14

POSITIVE LOGITS

erm

0.17

ãĥ³ãĥĶ

0.15

hev

0.15

ìĩ

0.15

urger

0.14

desc

0.14

uhl

0.14

 ÙħØŃÙĦ

0.14

/browse

0.14

iais

0.14

Activations Density 0.024%

metadata and descriptive elements in API documentation

No Comments

No Known Activations