INDEX

Explanations

phrases related to receiving or obtaining something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

edx

-0.13

ustr

-0.13

ements

-0.13

plements

-0.13

ilo

-0.13

ieder

-0.13

/dom

-0.13

antu

-0.13

wr

-0.13

POSITIVE LOGITS

abei

0.17

ellular

0.17

-translate

0.16

obus

0.16

aminer

0.16

folio

0.16

ichi

0.14

Kul

0.14

 Colleg

0.14

uppy

0.14

Activations Density 0.045%

phrases related to receiving or obtaining something

No Comments

No Known Activations