INDEX

Explanations

mathematical terms and concepts related to processes and distributions

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

 Ø§ÙĦØ¹ÙĤ

-0.14

ÎµÎ¯

-0.14

orent

-0.14

Quaternion

-0.14

afone

-0.13

ortho

-0.13

ħ§

-0.13

amide

-0.13

liga

-0.13

usat

-0.12

POSITIVE LOGITS

Po

0.29

 Mark

0.24

 process

0.24

 random

0.23

urn

0.22

 renewal

0.21

 processes

0.21

 Bern

0.21

 birth

0.20

Po

0.20

Activations Density 0.251%

mathematical terms and concepts related to processes and distributions

No Comments

No Known Activations