INDEX

Explanations

instances of the word "Yo"

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

bon

-0.18

ahead

-0.17

ÃŃm

-0.16

bon

-0.15

 Steele

-0.15

olan

-0.14

NavController

-0.13

ÑĶÐ¼

-0.13

-ahead

-0.13

èĹı

-0.13

POSITIVE LOGITS

Yo

0.25

Yo

0.24

yo

0.21

YO

0.20

yo

0.19

ãĥ¼ãĥĨ

0.16

-Y

0.16

landa

0.16

soy

0.15

Soy

0.15

Activations Density 0.006%

instances of the word "Yo"

No Comments

No Known Activations