INDEX

Explanations

phrases indicating timeframes related to the near future

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ilha

-0.14

 Platz

-0.14

formik

-0.14

quist

-0.13

 flavours

-0.13

 sustained

-0.13

mÄĽ

-0.13

ektor

-0.13

 longevity

-0.13

Dod

-0.12

POSITIVE LOGITS

 future

0.33

 near

0.30

future

0.26

near

0.26

 term

0.25

 tÆ°Æ¡ng

0.24

 Near

0.24

UTURE

0.24

Near

0.24

uture

0.23

Activations Density 0.016%

phrases indicating timeframes related to the near future

No Comments

No Known Activations