INDEX

Explanations

HTML attributes or tags within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

INGTON

-0.19

iro

-0.16

atica

-0.16

ÑĢÐ¸Ð¹

-0.15

iol

-0.15

ington

-0.15

eri

-0.15

ero

-0.15

 append

-0.15

alom

-0.14

POSITIVE LOGITS

¦¬

0.16

iev

0.15

 hoof

0.15

ÐŁÐļ

0.15

.scalablytyped

0.14

?>>

0.14

Ã¤d

0.14

edral

0.14

Ã©ny

0.14

ÑħÐ¸

0.14

Activations Density 0.049%

HTML attributes or tags within a document

No Comments

No Known Activations