INDEX

Explanations

mathematical symbols and terms related to probability and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.17

^-

-0.16

-0.15

ł

-0.14

Äįe

-0.14

Î¬

-0.13

 Mons

-0.13

.="

-0.13

ä¸Ŀ

-0.13

{-

-0.13

POSITIVE LOGITS

^{

0.49

ç¬¬

0.28

 ç¬¬

0.28

 thá»©

0.21

 perceived

0.20

 Perception

0.20

^{

0.19

 perception

0.19

 perce

0.16

ernote

0.14

Activations Density 0.063%

mathematical symbols and terms related to probability and statistics

No Comments

No Known Activations