INDEX

Explanations

technical terms related to programming and software implementation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ventus

-0.16

__;

-0.15

utsch

-0.15

à¤¾à¤Ĺà¤¤

-0.15

 Ø±Ø¦

-0.14

ÄħÅ¼

-0.14

onet

-0.14

.postValue

-0.14

.metro

-0.14

gatsby

-0.13

POSITIVE LOGITS

Ext

0.39

Ext

0.30

 xtype

0.27

-ext

0.25

Ext

0.25

EXT

0.24

ext

0.23

Cls

0.22

Sen

0.22

ext

0.21

Activations Density 0.007%

technical terms related to programming and software implementation

No Comments

No Known Activations