INDEX

Explanations

elements related to laws 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 dikke

-0.17

 Admir

-0.15

uum

-0.15

/thumb

-0.15

stad

-0.14

 Yunan

-0.14

awan

-0.14

 dÃ©t

-0.14

Kak

-0.14

POSITIVE LOGITS

 Â§Â§

0.20

 Â§

0.19

lex

0.17

irit

0.17

andro

0.16

erm

0.16

jur

0.15

Ink

0.15

à¸µà¸¢à¸¡

0.15

 norm

0.15

Activations Density 0.057%

elements related to laws and regulations

No Comments

No Known Activations