INDEX

Explanations

positive assessments of books and written works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 repr

-0.15

 happier

-0.15

fo

-0.15

uring

-0.15

 glorious

-0.14

 rebut

-0.14

ailable

-0.13

 succinct

-0.13

 beloved

-0.13

 Radi

-0.13

POSITIVE LOGITS

 informative

0.28

Inform

0.24

inform

0.23

 informat

0.23

 Inform

0.23

 informational

0.22

 enlight

0.22

eye

0.22

 instruct

0.21

 educational

0.20

Activations Density 0.192%

positive assessments of books and written works

No Comments

No Known Activations