INDEX

Explanations

metrics and performance indicators related to companies and financial data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

atura

-0.15

olem

-0.15

 Hava

-0.14

uros

-0.14

pered

-0.14

urm

-0.14

raya

-0.14

-0.13

omit

-0.13

ponge

-0.13

POSITIVE LOGITS

.CustomButton

0.13

 é»

0.13

Ø±Ø§Ùģ

0.13

NST

0.13

.Xtra

0.13

ollow

0.13

/parser

0.13

dzi

0.13

/gui

0.13

ipeg

0.13

Activations Density 0.012%

metrics and performance indicators related to companies and financial data

No Comments

No Known Activations