INDEX

Explanations

references to body weight and condition, particularly relating to fat and obesity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

eer

-0.19

oce

-0.16

itzer

-0.16

illard

-0.16

esine

-0.16

ingroup

-0.15

orf

-0.15

ingen

-0.15

auc

-0.15

hart

-0.15

POSITIVE LOGITS

igue

0.37

ality

0.32

ima

0.30

ig

0.28

uous

0.26

igu

0.25

ness

0.24

IMA

0.22

igure

0.22

ih

0.22

Activations Density 0.016%

references to body weight and condition, particularly relating to fat and obesity

No Comments

No Known Activations