INDEX

Explanations

mathematical concepts and terminology related to functions and mappings

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

alar

-0.15

ouv

-0.15

uku

-0.15

laÄį

-0.14

VERR

-0.14

ulfilled

-0.14

 validators

-0.14

.Parcelable

-0.14

 Vern

-0.13

ochastic

-0.13

POSITIVE LOGITS

 boundary

0.23

 surgery

0.22

 home

0.22

 handle

0.22

cob

0.21

 Surgery

0.21

 punct

0.21

 handles

0.21

dif

0.21

 Weinstein

0.21

Activations Density 0.110%

mathematical concepts and terminology related to functions and mappings

No Comments

No Known Activations