INDEX

Explanations

numerical data and references to dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

agrant

-0.18

ERA

-0.17

era

-0.16

Era

-0.14

aken

-0.14

ONGL

-0.14

Ã¥n

-0.14

tag

-0.14

 Matters

-0.14

wen

-0.14

POSITIVE LOGITS

ableViewController

0.17

ideon

0.15

.updateDynamic

0.14

$MESS

0.14

ulong

0.14

lek

0.14

0.13

 laut

0.13

\Tests

0.13

UIViewController

0.13

Activations Density 0.010%

numerical data and references to dates

No Comments

No Known Activations