INDEX

Explanations

mathematical notation and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

anta

-0.17

oga

-0.15

ANTA

-0.15

antt

-0.15

Ð°Ð½ÑĤÐ°

-0.15

pci

-0.14

ãĤ¹ãģ®

-0.14

icio

-0.14

oplevel

-0.14

ãģ°ãģĭãĤĬ

-0.14

POSITIVE LOGITS

0.16

arov

0.14

íİ¸

0.13

 cest

0.13

Facade

0.13

vor

0.13

emos

0.13

 Curtain

0.13

imest

0.13

 hÃ¡

0.13

Activations Density 0.112%

mathematical notation and symbols

No Comments

No Known Activations