INDEX

Explanations

medical terms and specializations related to neurology and surgery

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

ozem

-0.17

lier

-0.16

izo

-0.16

quete

-0.16

adin

-0.15

enderit

-0.15

ALLY

-0.14

ogi

-0.14

sik

-0.14

auce

-0.14

POSITIVE LOGITS

Å¯j

0.15

.nlm

0.15

uards

0.14

eparator

0.14

 regular

0.14

posables

0.14

ãĥ©ãĥ¼

0.13

multiline

0.13

smarty

0.13

Activations Density 0.025%

medical terms and specializations related to neurology and surgery

No Comments

No Known Activations