INDEX

Explanations

mathematical calculations and formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

cep

-0.15

.Restrict

-0.14

zi

-0.14

Fil

-0.14

/Branch

-0.13

zik

-0.13

zag

-0.13

roti

-0.13

 Sass

-0.13

mez

-0.13

POSITIVE LOGITS

 ratio

0.46

 Ratio

0.43

ratio

0.43

 ratios

0.42

Ratio

0.40

 dividing

0.40

 division

0.39

 divided

0.39

 Division

0.37

 quotient

0.35

Activations Density 0.224%

mathematical calculations and formulas

No Comments

No Known Activations