INDEX

Explanations

terms and annotations related to programming and database schema definitions

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

 true

-0.23

the

-0.21

 ((((

-0.19

 this

-0.19

str

-0.19

 value

-0.19

new

-0.18

set

-0.18

POSITIVE LOGITS

()↵

0.30

()

0.28

(↵

0.28

()↵↵

0.27

().

0.26

();↵

0.24

(name

0.23

(),↵

0.23

(**

0.23

();

0.22

Activations Density 0.017%

terms and annotations related to programming and database schema definitions

No Comments

No Known Activations