INDEX

Explanations

mentions of coffee

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

bes

-0.18

ning

-0.17

fully

-0.16

ners

-0.16

esen

-0.16

ally

-0.15

iger

-0.15

sects

-0.15

mie

-0.15

taj

-0.14

POSITIVE LOGITS

house

0.28

houses

0.24

 beans

0.24

 grounds

0.23

 bean

0.22

bean

0.21

 Bean

0.21

HOUSE

0.21

beans

0.21

/es

0.20

Activations Density 0.009%

mentions of coffee

No Comments

No Known Activations