INDEX

Explanations

references to durations of time, such as days, weeks, months, and years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ascus

-0.16

adata

-0.15

opoly

-0.15

utilus

-0.14

adaki

-0.14

erot

-0.14

à¸²à¸ĩ

-0.13

à¹Ģà¸Īà¸£

-0.13

à¥Īà¤®

-0.13

atham

-0.13

POSITIVE LOGITS

shy

0.38

 into

0.35

 short

0.28

 after

0.27

ago

0.27

 earlier

0.27

 prior

0.25

into

0.24

 removed

0.24

 before

0.24

Activations Density 0.048%

references to durations of time, such as days, weeks, months, and years

No Comments

No Known Activations