INDEX

Explanations

medical terms related to surgical procedures and bodily discomfort

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 sulph

-0.17

 annum

-0.17

omorphic

-0.16

è£

-0.15

 Gratis

-0.15

ANNEL

-0.14

enant

-0.14

emm

-0.14

Cly

-0.14

uder

-0.14

POSITIVE LOGITS

 Harm

0.17

may

0.17

:↵

0.17

 person

0.16

 medicines

0.16

 medicine

0.16

 tiny

0.16

wor

0.15

 abnormal

0.15

Activations Density 0.297%

medical terms related to surgical procedures and bodily discomfort

No Comments

No Known Activations