INDEX

Explanations

references to time and duration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

inÃ§

-0.15

 Hund

-0.15

æ¡Ĳ

-0.15

aira

-0.15

 Days

-0.15

iali

-0.15

pond

-0.14

.trailing

-0.14

Days

-0.14

 Brun

-0.14

POSITIVE LOGITS

 hour

0.46

 Hour

0.35

 hours

0.35

-hour

0.35

hour

0.34

 HOUR

0.34

Hour

0.30

å°ıæĹ¶

0.30

hours

0.29

 Hours

0.28

Activations Density 0.263%

references to time and duration

No Comments

No Known Activations