INDEX

Explanations

time durations or periods related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 HOUR

-0.15

echa

-0.14

Ø«Ø§Ø±

-0.13

eto

-0.13

stÃ¥

-0.13

jal

-0.13

ras

-0.13

eg

-0.13

à¸Ńà¸ĩ

-0.13

POSITIVE LOGITS

 worth

0.33

’

0.31

 Worth

0.26

worth

0.25

 minimum

0.23

 duration

0.22

-plus

0.20

 notice

0.19

 plus

0.19

Activations Density 0.095%

time durations or periods related to events

No Comments

No Known Activations