INDEX

Explanations

references to lions

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

undry

-0.19

anson

-0.17

alon

-0.15

alian

-0.15

amax

-0.15

alam

-0.15

urent

-0.14

TAG

-0.14

 rope

-0.14

ipv

-0.14

POSITIVE LOGITS

ess

0.31

esses

0.31

cub

0.26

 lion

0.24

ardo

0.23

 Lion

0.22

 mane

0.22

Cub

0.20

 lions

0.20

ESS

0.19

Activations Density 0.007%

references to lions

No Comments

No Known Activations