INDEX

Explanations

references to lions and the term 'lion' across 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

untime

-0.17

leston

-0.17

edy

-0.16

lov

-0.16

quisitions

-0.16

mer

-0.15

imer

-0.15

vip

-0.14

indr

-0.14

³

-0.14

POSITIVE LOGITS

ardo

0.22

ess

0.21

esses

0.21

 mane

0.20

URRED

0.19

 lion

0.19

 Lion

0.19

cub

0.18

 lions

0.18

Ã¡jem

0.17

Activations Density 0.014%

references to lions and the term 'lion' across various contexts

No Comments

No Known Activations