INDEX

Explanations

numerical representations related to time and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

undi

-0.16

oyo

-0.16

 dossier

-0.15

 timelines

-0.15

igli

-0.14

angered

-0.14

 Threshold

-0.14

Gaz

-0.14

enso

-0.14

series

-0.13

POSITIVE LOGITS

 hour

0.33

hour

0.30

 Hour

0.30

 minute

0.29

Hour

0.27

 HOUR

0.27

 hours

0.27

 minutes

0.25

å°ıæĹ¶

0.24

.hour

0.23

Activations Density 0.029%

numerical representations related to time and measurements

No Comments

No Known Activations