INDEX

Explanations

expressions of presenting, offering, or showcasing specific ideas or items

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

Realm

-0.17

-0.14

ITE

-0.14

AMES

-0.14

zon

-0.14

zb

-0.13

gig

-0.13

Lite

-0.13

 loose

-0.13

POSITIVE LOGITS

ocale

0.20

Multiplicity

0.18

tif

0.17

 ÑģÐ¾Ð±Ð¾Ð¹

0.17

ocado

0.16

/assert

0.16

rech

0.15

utterstock

0.15

çĵ

0.14

.scalablytyped

0.14

Activations Density 0.049%

expressions of presenting, offering, or showcasing specific ideas or items

No Comments

No Known Activations