INDEX

Explanations

statements that affirm or assert the quality or condition of something

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

apons

-0.15

ide

-0.15

isman

-0.14

onga

-0.14

ishing

-0.14

ãģĿãĤĵãģª

-0.14

Äĩe

-0.13

omb

-0.13

atorial

-0.13

uture

-0.13

POSITIVE LOGITS

why

0.30

why

0.26

 incident

0.22

 itself

0.19

 Incident

0.17

how

0.17

ä¸ºä»Ģä¹Ī

0.17

 Ð¿Ð¾ÑĩÐµÐ¼Ñĥ

0.17

Why

0.16

istrovstvÃŃ

0.16

Activations Density 0.082%

statements that affirm or assert the quality or condition of something

No Comments

No Known Activations