INDEX

Explanations

references to positions of authority or executive roles within companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

izzo

-0.19

ÎµÏħ

-0.17

Ã´me

-0.14

arus

-0.14

 GridLayout

-0.14

onas

-0.14

omain

-0.14

ostel

-0.14

inka

-0.14

obot

-0.14

POSITIVE LOGITS

 majority

0.33

 holding

0.32

 controlled

0.30

 parent

0.29

 listed

0.29

 wholly

0.27

controlled

0.27

 Holding

0.26

 Controlled

0.25

 Parent

0.25

Activations Density 0.145%

references to positions of authority or executive roles within companies

No Comments

No Known Activations