INDEX

Explanations

phrases and discussions related to predictions and possibilities for the future

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

otch

-0.16

itta

-0.15

lena

-0.15

supported

-0.14

aler

-0.14

ower

-0.14

otton

-0.14

.createObject

-0.14

urst

-0.14

retty

-0.13

POSITIVE LOGITS

 store

0.39

store

0.33

 Store

0.31

Store

0.30

 planned

0.29

 Planned

0.27

-store

0.26

.store

0.24

 stores

0.24

	store

0.24

Activations Density 0.052%

phrases and discussions related to predictions and possibilities for the future

No Comments

No Known Activations