INDEX

Explanations

coding elements and configurations in programming documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

uncio

-0.15

chem

-0.14

onom

-0.14

é¤¨

-0.14

å¤§åħ¨

-0.14

ãĥ¬ãĥ¼

-0.14

emek

-0.14

chl

-0.14

chema

-0.13

insky

-0.13

POSITIVE LOGITS

 Scenario

0.33

 scenario

0.32

Scenario

0.30

scenario

0.29

 scenarios

0.29

 Given

0.28

 given

0.27

 step

0.26

 steps

0.25

 GIVEN

0.25

Activations Density 0.023%

coding elements and configurations in programming documents

No Comments

No Known Activations