INDEX

Explanations

concepts related to fame and celebrity culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 independents

-0.16

izu

-0.15

idenav

-0.15

illis

-0.14

clang

-0.14

ipo

-0.14

 NÄĽm

-0.14

iap

-0.14

;set

-0.14

pta

-0.14

POSITIVE LOGITS

 celebrities

0.41

 celebrity

0.40

 cele

0.37

 stars

0.34

 star

0.28

 famous

0.28

-ce

0.27

cele

0.26

 Cele

0.26

 Celebrity

0.26

Activations Density 0.257%

concepts related to fame and celebrity culture

No Comments

No Known Activations