INDEX

Explanations

references to measuring devices and their functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Å¡t

-0.18

ess

-0.17

ÏĦÎµÎ¹

-0.14

ustr

-0.14

 anonymity

-0.14

iface

-0.13

Smy

-0.13

razier

-0.13

ibi

-0.13

erc

-0.13

POSITIVE LOGITS

/browse

0.17

azor

0.17

endoza

0.16

 Wayback

0.16

ulse

0.16

Ø®Ø§ÙĨÙĩ

0.15

bras

0.15

_Tis

0.14

ropolis

0.14

plib

0.14

Activations Density 0.009%

references to measuring devices and their functionalities

No Comments

No Known Activations