INDEX

Explanations

attributes related to book design and quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

åĪĴ

-0.16

oren

-0.15

bsd

-0.15

èĺ

-0.14

orer

-0.14

opup

-0.14

AINED

-0.13

å¼Ł

-0.13

Î±Î¹Î½

-0.13

ninger

-0.13

POSITIVE LOGITS

 binding

0.39

 bound

0.37

binding

0.34

 Binding

0.33

 bind

0.32

-bound

0.31

 bindings

0.31

bound

0.31

-binding

0.30

bind

0.30

Activations Density 0.061%

attributes related to book design and quality

No Comments

No Known Activations