INDEX

Explanations

financial metrics and calculations related to investments and returns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 statistics

-0.15

 averaging

-0.15

 Pron

-0.15

 sposÃ³b

-0.14

 numbering

-0.14

UX

-0.14

éĩı

-0.13

 YÃ¶n

-0.13

opensource

-0.13

statistics

-0.13

POSITIVE LOGITS

 total

0.27

net

0.26

 overall

0.26

 expected

0.24

 absolute

0.23

 effective

0.23

 mean

0.23

Net

0.22

 actual

0.21

 gross

0.21

Activations Density 0.415%

financial metrics and calculations related to investments and returns

No Comments

No Known Activations