INDEX

Explanations

references to healthcare and digital technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ø¶ÛĮ

-0.17

Ð»ÐµÐº

-0.17

plevel

-0.16

Msp

-0.15

 Wort

-0.15

/Instruction

-0.14

MMMM

-0.14

etxt

-0.14

odash

-0.13

SocketAddress

-0.13

POSITIVE LOGITS

 tracing

0.34

 contact

0.31

Trace

0.28

 trace

0.28

 Trace

0.27

 Contact

0.27

 TRACE

0.26

Contact

0.24

 traced

0.24

contact

0.24

Activations Density 0.037%

references to healthcare and digital technology

No Comments

No Known Activations