INDEX

Explanations

instances related to account management or references to accounts in a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ode

-0.21

burg

-0.17

dy

-0.17

ington

-0.17

fall

-0.16

angs

-0.16

zsche

-0.16

ilt

-0.15

keiten

-0.15

olution

-0.15

POSITIVE LOGITS

edly

0.17

nap

0.16

tit

0.15

raits

0.15

ikan

0.14

åĿĬ

0.14

ts

0.14

 iÃ§i

0.14

DrawerToggle

0.14

yonel

0.14

Activations Density 0.044%

instances related to account management or references to accounts in a system

No Comments

No Known Activations