INDEX

Explanations

function and method definitions in programming code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

(){

-0.16

áº·t

-0.16

bru

-0.15

antics

-0.15

dorf

-0.15

orer

-0.14

uns

-0.14

uman

-0.14

ardi

-0.14

uns

-0.13

POSITIVE LOGITS

 {↵

0.17

exion

0.15

{↵

0.14

iras

0.14

 abstract

0.14

à¸µà¸¢à¸ļ

0.14

 Killer

0.14

 ÐºÐ¾ÑĢÐ¼

0.13

_SECURE

0.13

isma

0.13

Activations Density 0.005%

function and method definitions in programming code

No Comments

No Known Activations