INDEX

Explanations

cooking instructions related to heat levels and cooking vessels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ç£¨

-0.15

hor

-0.15

hor

-0.14

 baked

-0.14

Å¡ak

-0.14

USTOM

-0.14

clair

-0.13

ic

-0.13

icut

-0.13

ichten

-0.13

POSITIVE LOGITS

 heat

0.28

 flames

0.24

 flame

0.23

heat

0.22

 Heat

0.22

 medium

0.21

Heat

0.21

medium

0.20

LOW

0.20

 Flames

0.19

Activations Density 0.018%

cooking instructions related to heat levels and cooking vessels

No Comments

No Known Activations