INDEX

Explanations

references to certification or credentialing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iesel

-0.17

.vertx

-0.17

erland

-0.16

Ã¡tka

-0.15

oÄŁlu

-0.15

ymous

-0.15

nings

-0.15

coli

-0.15

nist

-0.15

leine

-0.15

POSITIVE LOGITS

ainty

0.38

ificates

0.33

IFICATE

0.29

ainties

0.28

ifications

0.28

ification

0.27

ified

0.27

ifying

0.26

ific

0.24

aint

0.24

Activations Density 0.005%

references to certification or credentialing processes

No Comments

No Known Activations