INDEX

Explanations

content related to legal and medical claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

eru

-0.15

/cache

-0.15

ÑĮ

-0.14

Ø´ÙĪ

-0.14

Î½Î¹

-0.14

/archive

-0.14

Mev

-0.14

ÑĮÑİ

-0.13

 Donovan

-0.13

uv

-0.13

POSITIVE LOGITS

.TR

0.15

rouch

0.15

Ð¾Ð¿Ð¾Ð»

0.14

 tough

0.14

 Stir

0.14

ichi

0.14

uant

0.14

plex

0.13

Activations Density 0.102%

content related to legal and medical claims

No Comments

No Known Activations