INDEX

Explanations

numbers and numerical references in a context related to law and business

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

UTTON

-0.16

bung

-0.15

utton

-0.15

icont

-0.15

 æŁ

-0.15

ouro

-0.14

zent

-0.14

äºľ

-0.14

alach

-0.14

ettel

-0.14

POSITIVE LOGITS

erie

0.15

ussian

0.15

ALLERY

0.14

US

0.14

essler

0.14

erville

0.14

 bree

0.14

SError

0.14

Assignable

0.14

HorizontalAlignment

0.14

Activations Density 0.057%

numbers and numerical references in a context related to law and business

No Comments

No Known Activations