INDEX

Explanations

references to various forms of loss and the impact it has on situations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

lush

-0.15

ize

-0.15

utsch

-0.15

½

-0.15

tron

-0.14

itious

-0.14

 Orta

-0.14

 KÃ¼rt

-0.14

halt

-0.14

oppins

-0.14

POSITIVE LOGITS

(es

0.24

 mÃ¡t

0.23

ess

0.22

/change

0.21

lessly

0.21

es

0.20

 Prevention

0.19

 sustained

0.19

ses

0.19

Activations Density 0.032%

references to various forms of loss and the impact it has on situations or entities

No Comments

No Known Activations