INDEX

Explanations

keywords and phrases related to return values in programming functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

otas

-0.15

olly

-0.15

ged

-0.15

unce

-0.14

field

-0.14

tras

-0.14

bling

-0.14

ib

-0.14

 pylint

-0.14

Dos

-0.14

POSITIVE LOGITS

ulado

0.17

azer

0.17

ees

0.16

/send

0.16

Wunused

0.15

edException

0.15

ksiyon

0.15

erin

0.15

/Edit

0.14

mada

0.14

Activations Density 0.052%

keywords and phrases related to return values in programming functions

No Comments

No Known Activations