INDEX

Explanations

words and phrases related to estimates and numerical projections

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

owitz

-0.18

heit

-0.17

acha

-0.14

temps

-0.14

osl

-0.14

 barg

-0.14

vit

-0.14

 absol

-0.14

ÑĥÐºÐ¸

-0.14

 Harr

-0.14

POSITIVE LOGITS

 cÃ¢

0.15

andÄ±r

0.15

erus

0.14

.Resume

0.14

osterone

0.14

abic

0.13

ooth

0.13

gnu

0.13

.RunWith

0.13

gratis

0.13

Activations Density 0.034%

words and phrases related to estimates and numerical projections

No Comments

No Known Activations