INDEX

Explanations

mathematical notations and concepts related to equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

enders

-0.15

achu

-0.15

oq

-0.15

msp

-0.13

mav

-0.13

Calcul

-0.13

licensed

-0.13

 {{--<

-0.13

ourke

-0.13

POSITIVE LOGITS

 constants

0.42

 constant

0.37

constants

0.35

 Constants

0.35

 Constant

0.31

 parameters

0.31

Constants

0.31

constant

0.30

_constants

0.28

Constant

0.28

Activations Density 0.244%

mathematical notations and concepts related to equations

No Comments

No Known Activations