INDEX

Explanations

technical terminology related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ilde

-0.20

owied

-0.16

ieve

-0.15

vek

-0.15

acer

-0.15

-0.14

att

-0.14

ynn

-0.14

 ÐºÐ¸ÑĢ

-0.14

ampp

-0.13

POSITIVE LOGITS

 Little

0.26

 little

0.25

little

0.23

Little

0.23

 endian

0.21

 WORD

0.21

 word

0.20

 Word

0.19

Endian

0.18

_BE

0.18

Activations Density 0.081%

technical terminology related to programming and data structures

No Comments

No Known Activations