INDEX

Explanations

terms related to roles and responsibilities in a professional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

indsight

-0.16

thon

-0.14

Ľå»º

-0.14

ÑĥÑĢÑģ

-0.14

iny

-0.14

ivet

-0.14

ruary

-0.14

anou

-0.13

æį·

-0.13

ooks

-0.13

POSITIVE LOGITS

 roles

0.52

 role

0.51

 duties

0.45

 Roles

0.43

role

0.43

 Role

0.42

 ROLE

0.40

roles

0.39

-role

0.38

Role

0.38

Activations Density 0.329%

terms related to roles and responsibilities in a professional context

No Comments

No Known Activations