INDEX

Explanations

programming-related terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Kendrick

-0.17

rzy

-0.16

.cgi

-0.15

gil

-0.14

pcodes

-0.14

ê´Ģ

-0.14

rys

-0.14

æĶ¯

-0.14

.SetValue

-0.14

PointerType

-0.14

POSITIVE LOGITS

 toString

0.41

toString

0.40

ToString

0.36

 ToString

0.35

 tostring

0.32

.toString

0.31

.ToString

0.29

 repr

0.26

_repr

0.26

 representation

0.25

Activations Density 0.139%

programming-related terms and functions

No Comments

No Known Activations

programming-related terms and functions

No Comments

No Known Activations