INDEX

Explanations

mathematical references and notation related to theoretical physics concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

quo

-0.16

car

-0.16

bern

-0.15

alli

-0.15

ucht

-0.14

éĥ

-0.14

Kay

-0.14

ëĿ½

-0.14

 Bell

-0.14

Len

-0.14

POSITIVE LOGITS

 string

0.27

brane

0.24

string

0.23

 String

0.22

-string

0.21

 heter

0.21

String

0.20

 strings

0.20

 STRING

0.20

strings

0.19

Activations Density 0.011%

mathematical references and notation related to theoretical physics concepts

No Comments

No Known Activations