INDEX

Explanations

references to time durations or periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.15

 somehow

-0.15

frey

-0.14

 today

-0.14

elli

-0.14

 tomorrow

-0.14

ou

-0.14

POSITIVE LOGITS

 dozen

0.22

ìĶ©

0.19

/month

0.18

 Ð´ÐµÑģÑıÑĤ

0.17

éĴŁ

0.16

presso

0.16

ë£Į

0.16

ãĥ¼ãĥģ

0.15

 hundred

0.15

 thousand

0.14

Activations Density 0.051%

references to time durations or periods

No Comments

No Known Activations