INDEX

Explanations

references to the reader or direct addresses to "you."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

oyer

-0.15

BlockSize

-0.15

 commission

-0.14

iÃª

-0.14

uet

-0.14

creativecommons

-0.13

.instrument

-0.13

PLL

-0.13

Reviewed

-0.13

eday

-0.13

POSITIVE LOGITS

strup

0.17

ocard

0.16

zc

0.15

inal

0.14

.scalablytyped

0.14

conds

0.14

 Conn

0.14

/us

0.14

 meiden

0.14

Activations Density 0.086%

references to the reader or direct addresses to "you."

No Comments

No Known Activations

references to the reader or direct addresses to "you."

No Comments

No Known Activations