INDEX

Explanations

references to specific individuals or their roles in the context of professional or academic expertise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ÐłÐĺ

-0.17

ÑĪÐ»Ð¾

-0.15

icken

-0.15

">//

-0.15

eterangan

-0.15

è³¢

-0.15

prend

-0.15

omination

-0.15

ToBounds

-0.14

xEF

-0.14

POSITIVE LOGITS

 care

0.24

Care

0.20

-care

0.19

 Care

0.19

 stay

0.18

care

0.18

 caring

0.18

 Carey

0.18

 best

0.17

 fall

0.16

Activations Density 0.011%

references to specific individuals or their roles in the context of professional or academic expertise

No Comments

No Known Activations