INDEX

Explanations

mathematical or scientific labels and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 algorithms

-0.14

 Algorithms

-0.14

 section

-0.13

callbacks

-0.13

 sections

-0.13

obbies

-0.12

lfw

-0.12

å·

-0.12

#af

-0.12

Callbacks

-0.12

POSITIVE LOGITS

eq

0.50

eq

0.48

Eq

0.45

.eq

0.40

_eq

0.40

Eq

0.39

(eq

0.38

Equ

0.38

:eq

0.38

 equation

0.37

Activations Density 0.092%

mathematical or scientific labels and equations

No Comments

No Known Activations