INDEX

Explanations

mathematical terminologies and expressions 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.16

 Lambert

-0.16

unts

-0.15

leDb

-0.14

.rd

-0.14

é§

-0.14

sville

-0.14

addock

-0.13

untu

-0.13

POSITIVE LOGITS

 prime

0.22

 Prime

0.20

Prime

0.19

prime

0.18

 factor

0.17

ç´ł

0.17

 primes

0.17

 factors

0.17

abar

0.17

gcd

0.16

Activations Density 0.042%

mathematical terminologies and expressions related to equations and functions

No Comments

No Known Activations