INDEX

Explanations

mathematical notations and symbols typically used in equations and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

rel

-0.15

ambre

-0.15

rij

-0.14

piece

-0.14

nat

-0.14

">//

-0.14

zp

-0.14

 Maiden

-0.14

emes

-0.13

POSITIVE LOGITS

çļ

0.15

atat

0.15

agus

0.14

ared

0.14

Orn

0.14

aris

0.14

ulum

0.14

 trung

0.14

unctuation

0.13

 mobil

0.13

Activations Density 0.248%

mathematical notations and symbols typically used in equations and expressions

No Comments

No Known Activations