INDEX

Explanations

programming structures and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âĶĶ

-0.15

noinspection

-0.14

Unchecked

-0.14

ttp

-0.13

asd

-0.13

@testable

-0.13

kin

-0.13

uger

-0.13

_EXPORT

-0.13

endez

-0.13

POSITIVE LOGITS

 /**↵

0.26

 /*↵

0.25

/*

0.23

#region

0.20

/*↵

0.18

/**↵

0.18

 /**č↵

0.18

 /↵

0.17

/**

0.17

ehr

0.17

Activations Density 0.200%

programming structures and function definitions

No Comments

No Known Activations