INDEX

Explanations

cooking instructions and ingredients in recipes

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

isay

-0.15

 etiqu

-0.14

assandra

-0.14

cott

-0.14

 ÑĥÐ³Ð»

-0.14

ampoo

-0.14

 testcase

-0.14

angkan

-0.14

è°±

-0.14

.Singleton

-0.13

POSITIVE LOGITS

pap

0.28

 Worce

0.24

th

0.24

sea

0.23

Tab

0.23

 salt

0.23

Cay

0.22

 Aleppo

0.22

wor

0.21

 garlic

0.21

Activations Density 0.033%

cooking instructions and ingredients in recipes

No Comments

No Known Activations