INDEX

Explanations

variations of the word "des."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

issance

-0.18

èĮĤ

-0.16

ybrid

-0.16

weis

-0.16

lotte

-0.16

soever

-0.16

à¸Ńà¸ģ

-0.15

.scalablytyped

-0.15

cip

-0.15

yms

-0.15

POSITIVE LOGITS

cribed

0.19

cribes

0.18

Des

0.17

 beat

0.17

iring

0.17

eda

0.16

(des

0.16

ãģ¹

0.16

DES

0.16

perate

0.15

Activations Density 0.030%

variations of the word "des."

No Comments

No Known Activations