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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

enment

-0.14

QN

-0.14

 outr

-0.14

.getObject

-0.14

.online

-0.14

á»ĳc

-0.14

usch

-0.13

/interfaces

-0.13

ó

-0.13

æį

-0.13

POSITIVE LOGITS

 thereof

0.17

 version

0.17

raman

0.16

Ðĩ

0.16

_Version

0.16

HEMA

0.16

 Version

0.16

kees

0.16

version

0.15

indows

0.15

Activations Density 0.288%

programming-related keywords and constructs

No Comments

No Known Activations