INDEX

Explanations

programming-related syntax and structure in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ropp

-0.19

rex

-0.15

ãĥ¼ãĥķ

-0.15

oyer

-0.14

inski

-0.14

ãĥĭãĥĥãĤ¯

-0.14

///<

-0.14

isin

-0.14

 dostan

-0.14

 Kaynak

-0.14

POSITIVE LOGITS

public

0.30

 class

0.27

 public

0.27

class

0.25

Public

0.18

final

0.18

 PUBLIC

0.17

@interface

0.17

_public

0.17

 final

0.16

Activations Density 0.012%

programming-related syntax and structure in code

No Comments

No Known Activations