INDEX

Explanations

academic language and terminology related to model proposals and evaluations

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

åľĴ

-0.15

Lint

-0.15

Latest

-0.15

Ð»ÐºÐ¸

-0.15

ober

-0.14

stin

-0.14

ritis

-0.14

hang

-0.14

 cref

-0.13

 famously

-0.13

POSITIVE LOGITS

emain

0.15

oret

0.14

*out

0.14

uhl

0.13

anager

0.13

 setId

0.13

efon

0.13

ovation

0.13

 Number

0.13

iture

0.12

Activations Density 0.089%

academic language and terminology related to model proposals and evaluations

No Comments

No Known Activations