INDEX

Explanations

concepts related to human emotions and societal constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ascade

-0.19

reso

-0.18

/packages

-0.16

blas

-0.15

eka

-0.15

afÃ¼r

-0.15

aris

-0.15

parator

-0.15

ideo

-0.15

rena

-0.14

POSITIVE LOGITS

0.15

 Jerry

0.15

 allegedly

0.15

spiel

0.14

 himself

0.14

 supposedly

0.14

 stages

0.14

 Suns

0.13

ä¾į

0.13

ism

0.13

Activations Density 0.231%

concepts related to human emotions and societal constructs

No Comments

No Known Activations