INDEX

Explanations

different forms and variations of UTF encoding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

indle

-0.18

itin

-0.17

izon

-0.16

jej

-0.15

ewitness

-0.15

Eug

-0.14

amar

-0.14

chwitz

-0.14

ziel

-0.14

erca

-0.14

POSITIVE LOGITS

/javascript

0.20

alah

0.17

/dataTables

0.16

à¹Īà¸Ńà¸ĩ

0.14

_STAR

0.14

.GetBytes

0.14

istique

0.14

_HERSHEY

0.14

airs

0.13

Activations Density 0.004%

different forms and variations of UTF encoding

No Comments

No Known Activations