INDEX

Explanations

significant numerical data and their associations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

asher

-0.17

ÙĨØ¯ÛĮ

-0.14

antu

-0.14

AGER

-0.13

 Hague

-0.13

pare

-0.13

ansson

-0.13

kÃ©

-0.13

PG

-0.13

iq

-0.13

POSITIVE LOGITS

UPI

0.15

grave

0.14

 '../../../../../

0.14

ettes

0.13

glich

0.13

xb

0.13

ddy

0.13

imentary

0.13

ãĥ£

0.13

gim

0.13

Activations Density 0.056%

significant numerical data and their associations in the text

No Comments

No Known Activations