INDEX

Explanations

technical terms related to software development and programming constructs

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

HX

-0.15

hx

-0.15

quez

-0.15

@(

-0.15

ouz

-0.14

PullParser

-0.14

ynet

-0.14

ika

-0.14

HK

-0.13

FormattedMessage

-0.13

POSITIVE LOGITS

 signals

0.27

 SIGNAL

0.26

Qt

0.26

 Signals

0.24

Signals

0.23

(QtGui

0.22

 signal

0.21

signals

0.21

 PyQt

0.21

(Qt

0.21

Activations Density 0.031%

technical terms related to software development and programming constructs

No Comments

No Known Activations