INDEX

Explanations

various expressions of rates, particularly in statistical or economic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ness

-0.21

naire

-0.19

thon

-0.18

/sn

-0.18

ROME

-0.17

tron

-0.16

nya

-0.16

Ð¾Ð·Ð´

-0.16

Î³ÎµÎ¹

-0.16

ãĥ«ãĥķ

-0.15

POSITIVE LOGITS

payer

0.29

(rate

0.23

.rate

0.20

istrovstvÃŃ

0.18

st

0.18

et

0.17

-setting

0.17

çİĩ

0.15

-limit

0.15

card

0.15

Activations Density 0.040%

various expressions of rates, particularly in statistical or economic contexts

No Comments

No Known Activations