INDEX

Explanations

patent-related information and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ardu

-0.15

 impression

-0.15

atars

-0.15

Jad

-0.15

ä¸įåĪ°

-0.14

teÅŁ

-0.14

esis

-0.14

 Madd

-0.14

ubre

-0.14

itou

-0.14

POSITIVE LOGITS

WO

0.23

ethod

0.20

 Claims

0.20

 Invent

0.20

 claims

0.19

IPC

0.19

ipc

0.19

Assign

0.18

 claim

0.18

claim

0.17

Activations Density 0.015%

patent-related information and classifications

No Comments

No Known Activations