INDEX

Explanations

instances of the word "to" used as an infinitive marker or preposition

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

.Util

-0.16

oire

-0.16

èİ·

-0.16

èģĺ

-0.15

 Delegate

-0.15

nech

-0.15

.GetAxis

-0.15

Invite

-0.14

rech

-0.14

åĿ¦

-0.14

POSITIVE LOGITS

 lead

0.24

 serve

0.24

 head

0.23

 represent

0.22

 help

0.21

act

0.21

 become

0.20

 manage

0.20

be

0.20

 helm

0.20

Activations Density 0.162%

instances of the word "to" used as an infinitive marker or preposition

No Comments

No Known Activations