INDEX

Explanations

phrases related to workplace policies and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Boone

-0.16

è¾¼ãģ¿

-0.16

ÐµÐ½Ð¸Ðµ

-0.14

etin

-0.14

LOUR

-0.14

ahlen

-0.14

 ÑĢÑĥÑħ

-0.14

Ð¿Ð°

-0.13

uos

-0.13

 meiden

-0.13

POSITIVE LOGITS

 Employment

0.24

Employees

0.23

 redundancy

0.23

 employee

0.23

 redund

0.23

 Equality

0.23

 employees

0.22

 Employees

0.22

 Employee

0.21

TU

0.21

Activations Density 0.030%

phrases related to workplace policies and responsibilities

No Comments

No Known Activations