INDEX

Explanations

numerical data, particularly related to statistics or counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 correspondent

-0.16

ivatel

-0.15

âķĹ

-0.15

aled

-0.15

kop

-0.15

aliz

-0.15

ulpt

-0.14

æ³Ĭ

-0.14

ialized

-0.14

 COPY

-0.13

POSITIVE LOGITS

rat

0.15

ffe

0.14

neum

0.14

ugg

0.14

UG

0.14

 Psych

0.14

Î¿Ïħ

0.14

end

0.13

-fe

0.13

ota

0.13

Activations Density 0.024%

numerical data, particularly related to statistics or counts

No Comments

No Known Activations