INDEX

Explanations

technical terms related to software development and build processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

NGX

-0.15

 floppy

-0.14

DevExpress

-0.14

 Plymouth

-0.13

 Corp

-0.13

corp

-0.13

.tencent

-0.13

 Minnesota

-0.13

cept

-0.13

eger

-0.13

POSITIVE LOGITS

 Scala

0.46

 scala

0.45

 scal

0.41

Scala

0.40

 Scal

0.40

scal

0.39

scala

0.38

.scala

0.36

_scal

0.35

-scal

0.34

Activations Density 0.016%

technical terms related to software development and build processes

No Comments

No Known Activations