INDEX

Explanations

programming terms and concepts related to data processing and performance optimization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

isko

-0.16

acey

-0.15

è¡Ĺéģĵ

-0.15

 Synd

-0.15

ÅĻej

-0.14

Å¡ak

-0.14

ponential

-0.14

mne

-0.14

á»ĭch

-0.14

Ð¾Ð¼ÐµÑĤ

-0.14

POSITIVE LOGITS

 Mapper

0.26

TextInput

0.24

map

0.23

 mapper

0.23

Map

0.23

 reducers

0.22

_mapper

0.21

.map

0.20

 TextInput

0.20

reducers

0.20

Activations Density 0.021%

programming terms and concepts related to data processing and performance optimization

No Comments

No Known Activations