INDEX

Explanations

instances of the word "split" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

het

-0.17

ensen

-0.16

WS

-0.16

hay

-0.15

erli

-0.15

sis

-0.15

urement

-0.15

 Pace

-0.15

hm

-0.15

POSITIVE LOGITS

ting

0.37

tered

0.30

tering

0.26

TING

0.25

ter

0.25

.Split

0.23

(split

0.22

 apart

0.22

tring

0.22

TERS

0.21

Activations Density 0.021%

instances of the word "split" and its variations

No Comments

No Known Activations