INDEX

Explanations

references to the term "Lady."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ander

-0.17

ters

-0.16

 maxx

-0.16

CEF

-0.15

ists

-0.15

nist

-0.15

 meisje

-0.15

heits

-0.15

krom

-0.15

Ã©ment

-0.14

POSITIVE LOGITS

 Gaga

0.29

bug

0.28

/man

0.24

bugs

0.23

bird

0.22

finger

0.20

like

0.20

killer

0.19

 Liberty

0.19

ships

0.19

Activations Density 0.013%

references to the term "Lady."

No Comments

No Known Activations