INDEX

Explanations

mathematical symbols and notation related to equations and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

xm

-0.15

wig

-0.15

orna

-0.15

<fieldset

-0.15

Configurer

-0.15

Invoker

-0.14

urlencode

-0.14

 Boulevard

-0.14

âĢĮØ¯

-0.14

oug

-0.14

POSITIVE LOGITS

mans

0.19

å¯Ł

0.18

 Mans

0.15

/no

0.14

atz

0.14

frey

0.13

heim

0.13

ipt

0.13

elow

0.13

istant

0.13

Activations Density 0.045%

mathematical symbols and notation related to equations and functions

No Comments

No Known Activations