INDEX

Explanations

phrases that indicate factors or influences related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

.twimg

-0.14

ial

-0.14

kenin

-0.13

mana

-0.13

/she

-0.13

à¹Ģà¸¥à¸¢

-0.13

 ÑģÐ¾Ð±Ñĸ

-0.13

onical

-0.13

ses

-0.13

agua

-0.13

POSITIVE LOGITS

/by

0.22

/about

0.21

neath

0.20

wards

0.20

the

0.19

ness

0.17

/out

0.16

st

0.16

ward

0.15

Activations Density 0.317%

phrases that indicate factors or influences related to various subjects

No Comments

No Known Activations