INDEX

Explanations

information related to templates and invoice formatting

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

à¸ļà¸Ĺ

-0.15

AdapterFactory

-0.14

anza

-0.14

izzes

-0.14

Spoiler

-0.13

 ALOG

-0.13

;++

-0.13

/testify

-0.13

whelming

-0.13

ANI

-0.13

POSITIVE LOGITS

 samples

0.28

 sample

0.28

 templates

0.27

 Samples

0.26

 Templates

0.25

 template

0.25

 Sample

0.24

 examples

0.24

templates

0.23

 word

0.23

Activations Density 0.027%

information related to templates and invoice formatting

No Known Activations