INDEX

Explanations

phrases indicating time periods or durations

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

%X

-0.16

angan

-0.14

Ã©rt

-0.14

anmar

-0.14

anus

-0.14

igel

-0.14

ateral

-0.14

jt

-0.14

æĢĿãģĦ

-0.13

whole

-0.13

POSITIVE LOGITS

 years

0.31

 decades

0.27

 quarters

0.24

 months

0.23

years

0.23

-plus

0.22

 summers

0.22

 editions

0.21

 weeks

0.20

 couple

0.20

Activations Density 0.052%

phrases indicating time periods or durations

No Comments

No Known Activations