INDEX

Explanations

terms related to orthopedics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

vier

-0.14

YST

-0.14

&(

-0.14

erland

-0.14

bst

-0.14

uge

-0.14

otte

-0.14

berapa

-0.14

ctors

-0.14

ATTERY

-0.14

POSITIVE LOGITS

oley

0.16

enty

0.15

 inherited

0.14

dent

0.14

uld

0.14

edic

0.14

asion

0.14

ruk

0.14

::/

0.14

Î¼ÏĮ

0.13

Activations Density 0.006%

terms related to orthopedics

No Comments

No Known Activations