INDEX

Explanations

expressions of satisfaction or approval regarding products or services

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

obo

-0.16

iel

-0.15

nez

-0.15

uel

-0.15

elop

-0.14

ìŀ¥ìĿĦ

-0.14

erk

-0.14

-fontawesome

-0.14

ortex

-0.13

SError

-0.13

POSITIVE LOGITS

 overall

0.29

ingly

0.24

/conf

0.23

ably

0.23

overall

0.22

ly

0.22

 satisfaction

0.22

edly

0.22

Overall

0.21

 satisfied

0.20

Activations Density 0.046%

expressions of satisfaction or approval regarding products or services

No Comments

No Known Activations