INDEX

Explanations

statements regarding the presence or absence of certain qualities or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

two

-0.21

 chances

-0.17

éĤ£äºĽ

-0.17

ä¸¤ä¸ª

-0.17

 three

-0.16

two

-0.16

 twin

-0.16

dva

-0.15

 meisten

-0.15

 circumstances

-0.14

POSITIVE LOGITS

 stuff

0.27

 footage

0.23

 Machinery

0.22

 evidence

0.21

 machinery

0.19

stuff

0.19

 legislation

0.19

 Legislation

0.19

 groundwork

0.18

 informatie

0.18

Activations Density 0.557%

statements regarding the presence or absence of certain qualities or situations

No Comments

No Known Activations