INDEX

Explanations

terms related to law and legal practice

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

lick

-0.15

zers

-0.14

ÑģÑĸ

-0.14

Ã©ri

-0.14

 Customer

-0.14

acet

-0.14

 Sector

-0.14

idelberg

-0.14

-0.13

POSITIVE LOGITS

 Fortune

0.24

 closely

0.18

 real

0.17

Ã©sz

0.17

 fortune

0.17

 publicly

0.16

 privately

0.15

ãĤ½ãĥ³

0.15

ç²¾åĵģ

0.15

 NCAA

0.15

Activations Density 0.156%

terms related to law and legal practice

No Comments

No Known Activations