INDEX

Explanations

references to built-in functions and libraries in Python code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ajs

-0.15

æŁ³

-0.14

elay

-0.14

argout

-0.14

ussen

-0.14

ovah

-0.14

.setter

-0.13

tabpanel

-0.13

ë¡±

-0.13

enko

-0.13

POSITIVE LOGITS

 built

0.35

 builtin

0.34

 native

0.32

builtin

0.32

built

0.31

 Built

0.30

_builtin

0.29

native

0.27

Built

0.27

-built

0.25

Activations Density 0.260%

references to built-in functions and libraries in Python code

No Comments

No Known Activations