INDEX

Explanations

references to a specific individual or entity named "Yo" in various contexts

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

ÃŃm

-0.17

ect

-0.15

ahead

-0.15

 Steele

-0.15

AMP

-0.14

umble

-0.14

usi

-0.14

coni

-0.14

hrad

-0.14

POSITIVE LOGITS

Yo

0.22

Yo

0.21

yo

0.18

hei

0.17

anian

0.16

-Y

0.16

YO

0.16

annis

0.16

ãĥ¼ãĥĨ

0.15

Perl

0.15

Activations Density 0.011%

references to a specific individual or entity named "Yo" in various contexts

No Comments

No Known Activations