INDEX

Explanations

occurrences of numbers and mathematical expressions

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

.scalablytyped

-0.18

lag

-0.15

\grid

-0.15

ycastle

-0.15

ÑģÐ°Ð¼

-0.14

atÃ³

-0.14

lat

-0.14

rypted

-0.14

ertino

-0.14

urname

-0.14

POSITIVE LOGITS

0.27

 sixth

0.26

 Sixth

0.23

 tomorrow

0.18

 Tomorrow

0.17

jun

0.17

ĸ

0.17

à¥¬

0.16

ites

0.16

Tomorrow

0.16

Activations Density 0.094%

occurrences of numbers and mathematical expressions

No Comments

No Known Activations