INDEX

Explanations

references to regulatory agencies and medical organizations related to drugs and food

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

Negative Logits

eli

-0.15

aceous

-0.15

_capability

-0.14

åµ

-0.14

raise

-0.14

_Desc

-0.14

Äįil

-0.13

opsis

-0.13

UFFIX

-0.13

ÄįÃŃ

-0.13

POSITIVE LOGITS

 agency

0.23

 Administration

0.23

 Agency

0.23

 administration

0.22

 Bureau

0.21

agency

0.21

 Commission

0.20

 administrations

0.19

Agency

0.18

 Association

0.17

Activations Density 0.138%

references to regulatory agencies and medical organizations related to drugs and food

No Known Activations