INDEX

Explanations

references to professional roles and job titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.24

 Etsy

-0.21

 Facebook

-0.20

 Brexit

-0.20

Facebook

-0.19

aaS

-0.18

 Obama

-0.18

 WikiLeaks

-0.18

Û²Û°Û±

-0.18

 facebook

-0.18

POSITIVE LOGITS

RCA

0.27

 Mobil

0.23

ITT

0.23

 General

0.22

 Standard

0.22

 Yugosl

0.21

 Consolid

0.21

 USSR

0.21

 Soviet

0.21

 Yugoslavia

0.20

Activations Density 0.192%

references to professional roles and job titles

No Comments

No Known Activations