INDEX

Explanations

references to government agencies and regulatory bodies related to health and drugs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

otto

-0.14

à¸ļà¸Ĺ

-0.14

ittal

-0.13

weit

-0.13

aceous

-0.13

 åĩ

-0.13

Äįin

-0.13

ipped

-0.13

ique

-0.13

raise

-0.13

POSITIVE LOGITS

 agency

0.25

 Agency

0.24

 Commission

0.24

 Association

0.23

agency

0.21

Agency

0.20

Association

0.19

 organization

0.18

 Institute

0.18

 Corporation

0.18

Activations Density 0.174%

references to government agencies and regulatory bodies related to health and drugs

No Comments

No Known Activations