INDEX

Explanations

programming-related keywords and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

lÃ©d

-0.16

æ

-0.16

steen

-0.14

 Gutenberg

-0.14

edics

-0.14

 kÃ¶ln

-0.14

à¸Ħà¸¥

-0.13

utenberg

-0.13

obra

-0.13

_NOP

-0.13

POSITIVE LOGITS

 express

0.34

 Express

0.33

Express

0.32

express

0.31

 bodyParser

0.26

 EXPRESS

0.25

 middleware

0.24

(req

0.24

(express

0.23

req

0.23

Activations Density 0.026%

programming-related keywords and constructs

No Comments

No Known Activations