INDEX

Explanations

phrases related to rules and requirements in programming or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

]=>

-0.15

shr

-0.14

 agendas

-0.14

 parach

-0.14

angs

-0.14

 vengeance

-0.14

isse

-0.14

Ð»Ð°Ð³Ð¾Ð´

-0.14

iliz

-0.14

antry

-0.14

POSITIVE LOGITS

ÎµÏģÎ¹

0.15

ÑĢÐ¸Ð³

0.14

Gear

0.14

lie

0.14

CAA

0.13

bury

0.13

zano

0.13

 Tomas

0.13

Ãºi

0.13

.rect

0.13

Activations Density 0.088%

phrases related to rules and requirements in programming or specifications

No Comments

No Known Activations