INDEX

Explanations

references to funding allocations and tax-related discussions

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

 reverse

-0.15

Hed

-0.15

uddy

-0.14

iaz

-0.14

aul

-0.14

elen

-0.13

sil

-0.13

ival

-0.13

alu

-0.13

 Father

-0.13

POSITIVE LOGITS

 taxes

0.29

tax

0.25

 taxation

0.22

ç¨İ

0.22

tax

0.21

 Taxes

0.21

 fees

0.20

Tax

0.19

 taxa

0.19

 sales

0.18

Activations Density 0.088%

references to funding allocations and tax-related discussions

No Comments

No Known Activations