INDEX

Explanations

expressions of gratitude and thanks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 ease

-0.20

itti

-0.15

 Ease

-0.15

zung

-0.15

ipur

-0.15

ibur

-0.15

iti

-0.15

ç«ĭãģ¦

-0.14

\OptionsResolver

-0.14

_nsec

-0.14

POSITIVE LOGITS

ozem

0.18

antz

0.17

ar

0.15

riad

0.14

ewriter

0.14

-REAL

0.13

ìĽĲìĿ´

0.13

avras

0.13

 ÐĹÐ°Ð³

0.13

olist

0.13

Activations Density 0.061%

expressions of gratitude and thanks

No Comments

No Known Activations