INDEX

Explanations

references to unconventional or challenging food experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 hack

-0.16

Gay

-0.15

 ÐºÑĢÐ¾Ðº

-0.15

 skull

-0.15

flies

-0.14

 hacking

-0.14

Elf

-0.14

ÑģÑĤÑĥÐ¿

-0.14

 kern

-0.14

.Binding

-0.14

POSITIVE LOGITS

 tent

0.35

 Tent

0.34

tent

0.29

 jelly

0.24

cn

0.21

 tents

0.21

nem

0.20

zo

0.20

 Jelly

0.19

è§¦

0.19

Activations Density 0.029%

references to unconventional or challenging food experiences

No Comments

No Known Activations