INDEX

Explanations

references to specific mathematical concepts and theorems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

atoria

-0.17

-0.16

zell

-0.15

ppo

-0.14

inkel

-0.14

omez

-0.14

awan

-0.14

 Bosch

-0.13

acob

-0.13

ence

-0.13

POSITIVE LOGITS

/*č↵

0.16

Ãªnh

0.16

rowable

0.14

ÄĲT

0.14

kah

0.14

/xhtml

0.14

asto

0.14

 Ð´Ð¾Ð»

0.13

Ã¡ce

0.13

edException

0.13

Activations Density 0.122%

references to specific mathematical concepts and theorems

No Comments

No Known Activations