INDEX

Explanations

abbreviations and acronyms related to scientific and medical terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ERA

-0.15

icus

-0.15

ListOf

-0.14

_CONSOLE

-0.14

unar

-0.14

errat

-0.14

itag

-0.14

 Conserv

-0.13

_cash

-0.13

anik

-0.13

POSITIVE LOGITS

adora

0.15

iasi

0.14

htag

0.14

baj

0.13

Kay

0.13

acea

0.13

ador

0.13

ISCO

0.13

zia

0.13

Activations Density 0.047%

abbreviations and acronyms related to scientific and medical terms

No Comments

No Known Activations