INDEX

Explanations

product reviews or recommendations

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

Not in Any Lists

No Comments

Negative Logits

ucch

-0.15

rames

-0.14

AndView

-0.14

Ð»Ð°Ð´

-0.14

 Mold

-0.14

anon

-0.14

iÄħ

-0.13

èĭĹ

-0.13

 Cyan

-0.13

chip

-0.13

POSITIVE LOGITS

ex

0.31

 facial

0.24

ton

0.21

 gent

0.21

 cleans

0.21

ret

0.20

 face

0.20

 pore

0.20

ser

0.19

 Facial

0.19

Activations Density 0.023%

product reviews or recommendations

No Comments

No Known Activations