INDEX

Explanations

mathematical notation, specifically related to various variables and equations involving physical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

pled

-0.18

HELL

-0.17

á»Ńa

-0.15

aura

-0.14

aticon

-0.14

 hÃ¢l

-0.14

bulan

-0.14

 Hawkins

-0.14

é¼

-0.14

íĦ¸

-0.14

POSITIVE LOGITS

pez

0.19

eria

0.17

iss

0.17

Glo

0.16

ent

0.16

harma

0.15

eri

0.15

er

0.15

@section

0.14

éľĢ

0.14

Activations Density 0.142%

mathematical notation, specifically related to various variables and equations involving physical concepts

No Comments

No Known Activations