INDEX

Explanations

phrases indicating automatic or natural processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

.WebControls

-0.18

Ã¦k

-0.16

ãĥ

-0.15

ÑĩÐ¸ÑģÑĤ

-0.15

moh

-0.15

oke

-0.15

ood

-0.14

à¸ªà¸Ķ

-0.14

ellschaft

-0.14

voj

-0.14

POSITIVE LOGITS

 naturally

0.25

 natural

0.24

 Natural

0.22

Natural

0.21

natural

0.21

sen

0.18

 Naturally

0.17

èĩªçĦ¶

0.16

 automatically

0.15

nat

0.15

Activations Density 0.189%

phrases indicating automatic or natural processes

No Comments

No Known Activations