INDEX

Explanations

references to historical events, institutions, and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ublished

-0.16

ttp

-0.16

ÅĤu

-0.14

stride

-0.14

igne

-0.14

 reserved

-0.14

Published

-0.14

 Published

-0.14

imus

-0.13

owl

-0.13

POSITIVE LOGITS

led

0.45

 lead

0.33

 headed

0.31

Led

0.31

led

0.30

Led

0.30

 lider

0.29

 leadership

0.26

lead

0.25

 managed

0.24

Activations Density 0.299%

references to historical events, institutions, and entities

No Comments

No Known Activations