INDEX

Explanations

references to age or aging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ected

-0.18

arine

-0.15

ADOR

-0.14

 digest

-0.14

inent

-0.13

/order

-0.13

 Bent

-0.13

coni

-0.13

nett

-0.13

POSITIVE LOGITS

-fashioned

0.39

 fashioned

0.32

ÅĻich

0.25

-school

0.24

Ŀ

0.21

-old

0.20

/new

0.19

(er

0.19

/original

0.18

school

0.18

Activations Density 0.071%

references to age or aging

No Comments

No Known Activations