INDEX

Explanations

mathematical expressions and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.slim

-0.14

Elk

-0.14

aan

-0.14

dr

-0.14

 Unlimited

-0.14

 Infinite

-0.14

Gateway

-0.13

maal

-0.13

ienie

-0.13

 Antar

-0.13

POSITIVE LOGITS

 relations

0.19

relation

0.19

 relation

0.18

 relationship

0.18

 Relations

0.17

Relations

0.16

 relaciones

0.15

 relationships

0.15

relationship

0.15

relations

0.15

Activations Density 0.277%

mathematical expressions and notation

No Comments

No Known Activations