INDEX

Explanations

variations of the word "yellow."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 blue

-0.19

loo

-0.18

istor

-0.16

agan

-0.16

 purple

-0.15

zos

-0.15

ê²©

-0.15

 BLUE

-0.15

 Cunningham

-0.15

 dark

-0.14

POSITIVE LOGITS

/red

0.24

-yellow

0.22

-orange

0.21

ish

0.21

-green

0.18

ribbon

0.17

stein

0.17

aires

0.17

-headed

0.17

/or

0.17

Activations Density 0.011%

variations of the word "yellow."

No Comments

No Known Activations