INDEX

Explanations

technical terms and phrases related to engineering and system design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

arella

-0.15

 dese

-0.15

 æ»

-0.15

ipc

-0.14

aggi

-0.14

Ð¾Ð¹Ð½Ð¾

-0.14

dana

-0.14

atra

-0.14

 IconData

-0.14

 cong

-0.14

POSITIVE LOGITS

 Cousins

0.16

seau

0.15

.tc

0.14

lund

0.14

 Ster

0.14

levard

0.14

hap

0.14

Dur

0.14

ailability

0.13

olon

0.13

Activations Density 0.347%

technical terms and phrases related to engineering and system design

No Comments

No Known Activations