INDEX

Explanations

instructions related to cooking techniques and heat settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ekli

-0.15

hop

-0.15

ONGL

-0.14

Å¡ak

-0.14

ÐºÑĢÑĭ

-0.14

ç£¨

-0.14

 Laden

-0.14

clair

-0.14

ic

-0.13

/reference

-0.13

POSITIVE LOGITS

 heat

0.28

 medium

0.25

medium

0.22

 Heat

0.22

 settings

0.22

LOW

0.21

Heat

0.21

 flame

0.20

_heat

0.20

-medium

0.20

Activations Density 0.016%

instructions related to cooking techniques and heat settings

No Comments

No Known Activations