INDEX

Explanations

statistical terms and phrases indicating comparisons or results of scientific studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

empo

-0.17

adin

-0.15

 Harmony

-0.15

ÎķÎ¥

-0.15

ardÄ±m

-0.14

arnation

-0.14

ofile

-0.14

UNC

-0.14

bow

-0.14

eyse

-0.14

POSITIVE LOGITS

nor

0.27

nor

0.21

Nor

0.21

 neither

0.20

NOR

0.19

Nor

0.17

 mainstream

0.15

 cuck

0.15

EDI

0.15

awks

0.14

Activations Density 0.041%

statistical terms and phrases indicating comparisons or results of scientific studies

No Comments

No Known Activations