INDEX

Explanations

terms and phrases related to legal concepts and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

opup

-0.17

ritch

-0.15

ogo

-0.15

.rd

-0.15

 Wrest

-0.15

ugin

-0.15

zend

-0.15

Ã¡tico

-0.15

lep

-0.15

esen

-0.14

POSITIVE LOGITS

Ø¨Ø¹

0.18

ustr

0.17

 Conte

0.15

CommandEvent

0.15

 Hundred

0.14

bs

0.14

ffi

0.14

 updateUser

0.14

Bes

0.13

_GRANTED

0.13

Activations Density 0.002%

terms and phrases related to legal concepts and regulations

No Comments

No Known Activations