INDEX

Explanations

mathematical formulas and expressions related to products and factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.17

à¸²à¸ģ

-0.16

pig

-0.15

ologne

-0.15

odia

-0.14

 Shea

-0.14

_FUN

-0.14

 lateral

-0.14

-0.13

Pig

-0.13

POSITIVE LOGITS

aison

0.18

ysa

0.17

relude

0.17

aya

0.17

arsers

0.15

nge

0.15

ordan

0.15

emma

0.14

	UObject

0.14

arez

0.14

Activations Density 0.186%

mathematical formulas and expressions related to products and factors

No Comments

No Known Activations