INDEX

Explanations

comparisons and information regarding economic and production metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

edelta

-0.15

undos

-0.14

appers

-0.14

ertest

-0.13

loth

-0.13

ansa

-0.13

 dolu

-0.13

dur

-0.13

à¹Īà¸ĩ

-0.13

POSITIVE LOGITS

 twice

0.49

åĢį

0.44

 Twice

0.40

 times

0.39

times

0.37

-fold

0.36

tw

0.36

 fold

0.35

 TIMES

0.35

-times

0.34

Activations Density 0.209%

comparisons and information regarding economic and production metrics

No Comments

No Known Activations