INDEX

Explanations

references to menus and dining options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð¸Ð¼Ð¾

-0.17

INESS

-0.16

erness

-0.15

portun

-0.15

ModelProperty

-0.15

åł´

-0.14

(er

-0.13

ertime

-0.13

ness

-0.13

iness

-0.12

POSITIVE LOGITS

 items

0.31

 vitae

0.27

 item

0.26

 sheet

0.26

items

0.25

 builder

0.25

-items

0.24

 card

0.24

 Items

0.23

 entries

0.23

Activations Density 0.137%

references to menus and dining options

No Comments

No Known Activations