INDEX

Explanations

mention and references to celebrities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

stav

-0.21

 ÄĮer

-0.17

inton

-0.17

idas

-0.16

.scalablytyped

-0.16

 trÆ°á»Łng

-0.16

spir

-0.15

ners

-0.15

oko

-0.15

udios

-0.15

POSITIVE LOGITS

Cru

0.19

 chef

0.19

ved

0.18

ry

0.17

 endorsements

0.17

-status

0.17

 Chef

0.16

kest

0.15

 endorsement

0.15

LET

0.15

Activations Density 0.013%

mention and references to celebrities

No Comments

No Known Activations