INDEX

Explanations

technical terms related to programming and data management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

çĻ»

-0.15

Rated

-0.14

ancybox

-0.14

neau

-0.14

 Rated

-0.14

Lid

-0.14

 GÃ¼ven

-0.13

 subs

-0.13

circle

-0.13

ircles

-0.13

POSITIVE LOGITS

 cell

0.37

 Cell

0.33

 grid

0.31

 column

0.30

 cells

0.30

Cell

0.29

 Grid

0.29

-cell

0.29

_cell

0.28

 Cells

0.28

Activations Density 0.053%

technical terms related to programming and data management

No Comments

No Known Activations