INDEX

Explanations

instances of the word "ride" and its variations, indicating a focus on various forms of riding experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ted

-0.19

drawing

-0.17

ught

-0.16

á»Ĺ

-0.16

Histogram

-0.16

xing

-0.15

loe

-0.15

 Guth

-0.15

driver

-0.15

otate

-0.15

POSITIVE LOGITS

 shotgun

0.24

 Shotgun

0.21

 ride

0.21

/dr

0.20

hare

0.19

 rides

0.19

 rough

0.18

ocker

0.18

 horses

0.18

 Riding

0.17

Activations Density 0.019%

instances of the word "ride" and its variations, indicating a focus on various forms of riding experiences

No Comments

No Known Activations