INDEX

Explanations

numerical or date-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Pell

-0.16

á»ĥm

-0.15

ryan

-0.15

å¤§åħ¨

-0.15

 relig

-0.15

olson

-0.15

æĸ¹

-0.14

religious

-0.14

 subs

-0.14

jÃŃt

-0.14

POSITIVE LOGITS

 Ø¯Ø±Ø³

0.18

-Series

0.17

audi

0.17

 Series

0.17

 series

0.17

 readings

0.17

series

0.16

 lesson

0.16

(series

0.16

zan

0.16

Activations Density 0.122%

numerical or date-related information

No Comments

No Known Activations