INDEX

Explanations

mathematical symbols and notations related to formal equations and processes

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

quip

-0.16

 Tomorrow

-0.15

nip

-0.15

Ð»ÐµÐ²

-0.15

 Leather

-0.14

Tip

-0.14

èģ

-0.14

loy

-0.14

eldorf

-0.13

ISA

-0.13

POSITIVE LOGITS

imes

0.54

extr

0.33

 times

0.32

times

0.31

-times

0.28

.times

0.28

Times

0.27

ensor

0.26

_times

0.26

 Times

0.25

Activations Density 0.013%

mathematical symbols and notations related to formal equations and processes

No Comments

No Known Activations