INDEX

Explanations

references to legal opinions and judicial decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 indoor

-0.16

ufs

-0.15

oren

-0.14

STD

-0.14

 Mary

-0.14

 outdoor

-0.14

èĥĮ

-0.14

regon

-0.14

 Hancock

-0.14

POSITIVE LOGITS

 Patent

0.27

 patent

0.25

Pat

0.20

Pat

0.20

.pat

0.20

(pat

0.20

pat

0.19

 examiner

0.18

 Ð¿Ð°ÑĤ

0.18

Trademark

0.17

Activations Density 0.012%

references to legal opinions and judicial decisions

No Comments

No Known Activations