INDEX

Explanations

mathematical expressions and concepts related to algebra and category theory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

unte

-0.15

anas

-0.14

asons

-0.14

odb

-0.14

OLUM

-0.13

æ¢¯

-0.13

avers

-0.13

ho

-0.13

 Markus

-0.13

ables

-0.13

POSITIVE LOGITS

Gal

0.26

 field

0.26

 rings

0.24

 ring

0.24

 Field

0.23

 fields

0.23

 FIELD

0.23

-degree

0.21

ring

0.21

Gal

0.21

Activations Density 0.027%

mathematical expressions and concepts related to algebra and category theory

No Comments

No Known Activations