INDEX

Explanations

references to available services and options

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

rios

-0.17

ajs

-0.15

amoto

-0.15

Slf

-0.15

ucch

-0.14

egie

-0.14

 WINAPI

-0.14

enville

-0.14

ãĤ¦ãĥĪ

-0.14

ennon

-0.14

POSITIVE LOGITS

 available

1.14

available

0.99

 Available

0.97

Available

0.90

-available

0.88

 availability

0.88

 AVAILABLE

0.86

 disponible

0.85

_available

0.83

 disponibles

0.82

Activations Density 0.357%

references to available services and options

No Comments

No Known Activations