INDEX

Explanations

phrases that describe notable or noteworthy events or changes

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

IFE

-0.15

æľīçļĦ

-0.15

odore

-0.14

ÑģÑĮÐ¾Ð³Ð¾

-0.14

pora

-0.14

/*č↵

-0.14

ÑĥÐ»Ñİ

-0.14

ouden

-0.14

aoke

-0.13

Ð»Ð°ÑģÑĤÐ¸

-0.13

POSITIVE LOGITS

 nutshell

0.26

 recent

0.25

 twist

0.22

era

0.21

 society

0.21

recent

0.21

 effort

0.20

 sense

0.19

Nut

0.19

 earlier

0.19

Activations Density 0.048%

phrases that describe notable or noteworthy events or changes

No Comments

No Known Activations