INDEX

Explanations

attributes related to unique product designs and features

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

swick

-0.17

elves

-0.15

acula

-0.15

ubic

-0.13

/Instruction

-0.13

etros

-0.12

wen

-0.12

 Cour

-0.12

utow

-0.12

POSITIVE LOGITS

âĢŀP

0.14

 lyon

0.14

.Sin

0.13

sted

0.13

âĢŀM

0.13

Å©

0.13

 ÑģÐ¿ÑĢÐ°Ð²

0.12

OAD

0.12

argent

0.12

dÃŃ

0.12

Activations Density 1.424%

attributes related to unique product designs and features

No Comments

No Known Activations