INDEX

Explanations

function definitions and their associated attributes 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

affen

-0.15

isen

-0.15

 ëĭ

-0.14

OOM

-0.14

str

-0.14

 ++↵

-0.14

 ÐºÑĢÐ¾Ð²

-0.14

eti

-0.14

 rend

-0.13

traits

-0.13

POSITIVE LOGITS

:^(

0.17

AllWindows

0.16

={({

0.15

.glob

0.15

ãģĲ

0.14

çª

0.14

 Weiner

0.14

(lambda

0.14

ollar

0.14

park

0.14

Activations Density 0.196%

function definitions and their associated attributes in programming code

No Comments

No Known Activations