INDEX

Explanations

instances of the word "bear" and its variations, indicating a focus on concepts of endurance and support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

yle

-0.17

tz

-0.16

strar

-0.15

yu

-0.15

anity

-0.15

ching

-0.15

gens

-0.15

ULAR

-0.14

entre

-0.14

eteor

-0.14

POSITIVE LOGITS

 witness

0.36

 Witness

0.29

beiten

0.27

 fruit

0.23

ance

0.22

Witness

0.22

 testimony

0.21

 resemblance

0.21

fruit

0.21

Gry

0.20

Activations Density 0.021%

instances of the word "bear" and its variations, indicating a focus on concepts of endurance and support

No Comments

No Known Activations