INDEX

Explanations

symbols or special characters used in digital contexts

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

 Downs

-0.17

tie

-0.15

trace

-0.14

pond

-0.14

ANGO

-0.14

hread

-0.14

hed

-0.14

 Draft

-0.14

agoon

-0.14

 downs

-0.14

POSITIVE LOGITS

Åĳ

0.28

eli

0.26

Ã³l

0.25

an

0.23

Ã©li

0.23

esz

0.20

en

0.19

Ã¡ty

0.18

irt

0.18

esor

0.18

Activations Density 0.003%

symbols or special characters used in digital contexts

No Comments

No Known Activations