INDEX

Explanations

the presence of the word "like" as well as references to comparable things or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ø§Ø³ÙĬ

-0.17

ignon

-0.16

istrovstvÃŃ

-0.15

.scalablytyped

-0.14

arence

-0.14

kili

-0.14

inflate

-0.14

gni

-0.14

esModule

-0.13

arked

-0.13

POSITIVE LOGITS

-validator

0.14

 Terror

0.14

¼

0.14

allen

0.14

opleft

0.14

 /*!↵

0.13

GS

0.13

è´Ŀ

0.13

mar

0.13

.Appearance

0.13

Activations Density 0.069%

the presence of the word "like" as well as references to comparable things or examples

No Comments

No Known Activations