INDEX

Explanations

technical terms related to systems and algorithms in research

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

 seperate

-0.21

 seper

-0.20

 Various

-0.16

.utility

-0.15

amat

-0.15

ç¿¼

-0.15

latlong

-0.15

 utilise

-0.15

Various

-0.14

Ñĳ

-0.14

POSITIVE LOGITS

 itens

0.23

Â´s

0.23

 confort

0.22

 aprox

0.22

 Â¿

0.21

 previous

0.20

 frec

0.20

 nowadays

0.20

 evid

0.20

 appropriated

0.20

Activations Density 0.148%

technical terms related to systems and algorithms in research

No Comments

No Known Activations