INDEX

Explanations

numerical values and formatting characters typically used in code or mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ucci

-0.16

Rex

-0.15

ÃľR

-0.14

olie

-0.14

cke

-0.13

Ã¼re

-0.13

ereco

-0.13

è²¼

-0.13

anna

-0.13

acos

-0.13

POSITIVE LOGITS

0.13

.jav

0.13

 Werner

0.13

iple

0.13

 Carn

0.13

 erotico

0.13

Ð°Ð½ÑĸÑĹ

0.13

Activations Density 0.001%

numerical values and formatting characters typically used in code or mathematical expressions

No Comments

No Known Activations