INDEX

Explanations

terms related to patents and intellectual property

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

utdown

-0.16

ÑħÑĥ

-0.14

 ekip

-0.14

ÏĦÎ¿Î¹

-0.14

idor

-0.13

raphics

-0.13

vette

-0.13

å½¹

-0.13

RITE

-0.13

 Shutdown

-0.13

POSITIVE LOGITS

ee

0.24

ees

0.23

ability

0.21

 infringement

0.21

/IP

0.20

able

0.20

 HOLDERS

0.19

 office

0.18

 holders

0.18

 holder

0.17

Activations Density 0.009%

terms related to patents and intellectual property

No Comments

No Known Activations