INDEX

Explanations

terms related to employment benefits and health-related leave policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

lemn

-0.16

ungal

-0.15

æĪĲäºº

-0.15

 Erotische

-0.14

achel

-0.14

htmlspecialchars

-0.14

ãĥ³ãĤ°

-0.14

inke

-0.14

/cms

-0.14

ÐµÑĢÐµÑĩ

-0.14

POSITIVE LOGITS

 sick

0.22

 Sick

0.21

 sickness

0.18

 Attendance

0.17

 Employees

0.17

 leave

0.17

 leaves

0.17

FML

0.17

 absence

0.16

ENTA

0.16

Activations Density 0.035%

terms related to employment benefits and health-related leave policies

No Comments

No Known Activations