INDEX

Explanations

medical terminology related to diagnoses and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

asl

-0.20

rete

-0.16

awa

-0.15

ä¹¾

-0.15

anza

-0.15

emax

-0.15

íĴį

-0.14

alat

-0.14

opers

-0.14

gressor

-0.14

POSITIVE LOGITS

cy

0.19

Cy

0.15

Â¯Â¯Â¯Â¯

0.14

ìľ¡

0.14

Nah

0.14

 Derm

0.14

å¥½äºĨ

0.13

 best

0.13

 ground

0.13

 after

0.13

Activations Density 0.038%

medical terminology related to diagnoses and treatments

No Comments

No Known Activations