INDEX

Explanations

words related to food and dining experiences

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

 Sher

-0.17

acock

-0.15

ertools

-0.14

Æ°á»£u

-0.14

bows

-0.14

iola

-0.14

Sher

-0.14

-mf

-0.14

íĻķ

-0.14

pel

-0.13

POSITIVE LOGITS

bun

0.33

 sandwich

0.32

 SAND

0.30

sand

0.30

Sand

0.29

 sand

0.29

 sandwiches

0.27

 Sandwich

0.27

 slider

0.25

 burger

0.25

Activations Density 0.071%

words related to food and dining experiences

No Comments

No Known Activations