INDEX

Explanations

references to acting performances and the quality of actors in films

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

 Thema

-0.16

odash

-0.15

oppers

-0.15

 konkrÃ©t

-0.15

azon

-0.14

irts

-0.14

MeasureSpec

-0.14

ovel

-0.14

ampions

-0.14

ÑĢÐµÐ¼

-0.14

POSITIVE LOGITS

 convincing

0.18

 PERFORMANCE

0.17

 opposite

0.17

 nuances

0.17

 misc

0.16

 performance

0.16

 belie

0.16

 Ð¸Ð¼Ð¿

0.16

 facial

0.15

 chemistry

0.15

Activations Density 0.072%

references to acting performances and the quality of actors in films

No Comments

No Known Activations