INDEX

Explanations

terms related to oxidation and oxidants

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

nge

-0.18

Å©

-0.15

OwnProperty

-0.15

 Armstrong

-0.15

esda

-0.15

rÃ¼n

-0.14

tuk

-0.14

ATRIX

-0.14

rrha

-0.14

ormsg

-0.14

POSITIVE LOGITS

alic

0.29

ym

0.25

igen

0.24

yc

0.24

ides

0.24

bridge

0.23

idental

0.23

ford

0.22

tober

0.22

egen

0.22

Activations Density 0.017%

terms related to oxidation and oxidants

No Comments

No Known Activations