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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Conserv

-0.16

.openConnection

-0.15

 Bucket

-0.15

inned

-0.15

ward

-0.14

.INSTANCE

-0.14

Bucket

-0.14

Ð°Ð´ÐºÐ¸

-0.14

inerary

-0.14

ikh

-0.14

POSITIVE LOGITS

iage

0.16

UAGE

0.15

owie

0.15

dos

0.15

sleep

0.15

.bc

0.14

 emailAddress

0.14

Converted

0.14

 sleep

0.13

plib

0.13

Activations Density 0.007%

function and method definitions in programming code

No Comments

No Known Activations