INDEX

Explanations

descriptors that indicate quality, comfort, and user-friendliness

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

aco

-0.19

acob

-0.17

mnop

-0.15

otron

-0.15

tres

-0.15

ASN

-0.15

elong

-0.15

afi

-0.15

Builders

-0.15

ASC

-0.14

POSITIVE LOGITS

as

0.38

 than

0.23

 quanto

0.20

 possible

0.20

als

0.19

 ÐºÐ°Ðº

0.18

than

0.18

possible

0.17

 cÃłng

0.17

 possibile

0.17

Activations Density 0.083%

descriptors that indicate quality, comfort, and user-friendliness

No Comments

No Known Activations