INDEX

Explanations

expressions of strong emotions and reactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 cÃ©lib

-0.17

encies

-0.17

rades

-0.14

utas

-0.14

gam

-0.14

 mine

-0.14

-0.13

 fail

-0.13

ennes

-0.13

POSITIVE LOGITS

sup

0.16

arel

0.14

arend

0.14

 Ã§Ã¼nkÃ¼

0.14

chio

0.14

.POS

0.14

 Aerospace

0.14

 Mundo

0.14

<article

0.14

ìĻĦ

0.14

Activations Density 0.242%

expressions of strong emotions and reactions

No Comments

No Known Activations