INDEX

Explanations

references to acting and filmmaking, particularly related to debuts and directorial roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ewitness

-0.16

udson

-0.15

ucas

-0.14

bers

-0.14

ennes

-0.13

ruba

-0.13

.hr

-0.13

ereo

-0.13

atar

-0.13

POSITIVE LOGITS

 debut

0.76

deb

0.59

 debuted

0.54

 dÃ©but

0.48

deb

0.40

Deb

0.37

.deb

0.35

 maiden

0.34

 debit

0.28

 inaugural

0.28

Activations Density 0.094%

references to acting and filmmaking, particularly related to debuts and directorial roles

No Comments

No Known Activations