INDEX

Explanations

references to order and arrangement of information or elements

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

kee

-0.14

ongo

-0.14

uard

-0.14

·¨

-0.13

/moment

-0.13

 ÏĢÎ¿

-0.13

uhn

-0.12

 Ø¯Ø§Ùħ

-0.12

pcm

-0.12

å¾

-0.12

POSITIVE LOGITS

 order

0.56

éłĨ

0.47

 sequence

0.45

-order

0.44

order

0.44

é¡º

0.44

 ordering

0.42

 Order

0.41

 ORDER

0.41

 chron

0.41

Activations Density 0.280%

references to order and arrangement of information or elements

No Comments

No Known Activations