INDEX

Explanations

instances of the word "the" and other related determiner words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 item

-0.15

 actionTypes

-0.14

utters

-0.14

 ActionTypes

-0.13

 essentials

-0.13

uple

-0.13

 jaws

-0.13

 duel

-0.13

POSITIVE LOGITS

ses

0.28

è¿ĻäºĽ

0.22

éĤ£äºĽ

0.20

 various

0.17

äºĽ

0.17

 these

0.17

Ø§Ø¨Ø§Øª

0.17

anych

0.17

uds

0.16

 majority

0.16

Activations Density 0.559%

instances of the word "the" and other related determiner words

No Comments

No Known Activations