INDEX

Explanations

medical terminology related to conditions, treatments, and health metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

obe

-0.18

ophone

-0.16

averse

-0.15

icable

-0.15

OU

-0.14

 escape

-0.14

oreach

-0.13

ThreadPool

-0.13

orus

-0.13

 Incorporated

-0.13

POSITIVE LOGITS

aliz

0.16

agged

0.16

ÑĢÑĥÐ½

0.15

strup

0.15

 Mane

0.15

tÃ¼r

0.14

 copp

0.14

openh

0.14

buz

0.14

ermann

0.14

Activations Density 0.529%

medical terminology related to conditions, treatments, and health metrics

No Comments

No Known Activations