INDEX

Explanations

topics related to heavy objects or weight properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 welded

-0.19

 stainless

-0.17

 shower

-0.15

zzarella

-0.14

 showers

-0.14

scoped

-0.14

imuth

-0.14

 plÃ¡

-0.13

 electronics

-0.13

eki

-0.13

POSITIVE LOGITS

çĶ·åŃĲ

0.16

IGO

0.16

ignum

0.15

Animal

0.15

Canvas

0.14

Portable

0.14

eyh

0.14

animal

0.14

 Animal

0.14

Ð¸Ð»ÑĮ

0.14

Activations Density 0.193%

topics related to heavy objects or weight properties

No Comments

No Known Activations