INDEX

Explanations

mathematical notation and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

á»ĳi

-0.15

ë°ľ

-0.15

arel

-0.14

bob

-0.14

mediate

-0.14

imoto

-0.14

etti

-0.14

Ù

-0.14

ooth

-0.14

olec

-0.13

POSITIVE LOGITS

 convention

0.20

 conventions

0.19

Throughout

0.18

iyim

0.17

 Throughout

0.17

Convention

0.16

 prim

0.16

 Convention

0.16

 barr

0.15

OnError

0.15

Activations Density 0.073%

mathematical notation and expressions

No Comments

No Known Activations