INDEX

Explanations

mathematical notations and concepts related to convergence and sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ä¹ĭä¸Ģ

-0.19

ekil

-0.16

ìļ°

-0.15

èĨľ

-0.15

ereum

-0.14

oust

-0.14

lov

-0.14

åĪ»

-0.14

 gettimeofday

-0.14

ahkan

-0.14

POSITIVE LOGITS

prm

0.16

bserv

0.15

llib

0.14

å¤¢

0.14

onom

0.14

enton

0.14

igon

0.14

otos

0.13

 Babylon

0.13

Activations Density 0.302%

mathematical notations and concepts related to convergence and sequences

No Comments

No Known Activations