INDEX

Explanations

technical terms and concepts related to graph theory and network analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ctr

-0.15

opher

-0.14

yers

-0.14

ivent

-0.14

ope

-0.14

ÑĢÐ¸ÑĦ

-0.14

Zem

-0.14

opak

-0.14

elper

-0.13

½æķ°

-0.13

POSITIVE LOGITS

 structure

0.16

ì¶ĺ

0.16

/network

0.16

illion

0.15

 structures

0.15

CustomLabel

0.14

ãĥĭãĤ¢

0.14

ni

0.14

viz

0.14

uls

0.13

Activations Density 0.106%

technical terms and concepts related to graph theory and network analysis

No Comments

No Known Activations