INDEX

Explanations

coding-related keywords and components within a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.17

ãĥĥ

-0.16

ubber

-0.15

.nextSibling

-0.15

 Clothes

-0.14

lac

-0.14

ĶåĽŀ

-0.14

ilin

-0.14

 Kushner

-0.14

ober

-0.14

POSITIVE LOGITS

.class

0.57

 class

0.33

.self

0.28

class

0.26

.php

0.26

-class

0.23

:class

0.23

.java

0.22

	class

0.21

.getClass

0.21

Activations Density 0.028%

coding-related keywords and components within a programming context

No Comments

No Known Activations