INDEX

Explanations

actions related to consuming food

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Ø²Ø§ÙĨ

-0.17

anut

-0.16

chia

-0.15

Ø§ØªÛĮ

-0.15

zim

-0.15

ÐµÐ¼Ð¾

-0.15

crypt

-0.15

Ð°ÐºÑģÐ¸Ð¼

-0.15

vinc

-0.14

pole

-0.14

POSITIVE LOGITS

 chewing

0.23

 chew

0.23

 saliva

0.21

 mouth

0.20

åĶĩ

0.20

 Ð·ÑĥÐ±

0.20

-mouth

0.19

Jaw

0.19

 Mouth

0.18

 mouths

0.18

Activations Density 0.106%

actions related to consuming food

No Comments

No Known Activations