INDEX

Explanations

interactions and emotions among characters during conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ï¼Īç¬ĳ

-0.15

 impro

-0.14

à¹Ģà¸ĭà¸Ńà¸£

-0.14

obra

-0.14

 Beard

-0.13

ãĤıãĤĮ

-0.13

 Bren

-0.13

 Singer

-0.13

uhl

-0.13

ardash

-0.13

POSITIVE LOGITS

ifton

0.18

 Rarity

0.16

odia

0.16

Ä©

0.15

zbek

0.15

 tens

0.14

.chapter

0.14

tiv

0.14

regor

0.14

 Platinum

0.14

Activations Density 0.191%

interactions and emotions among characters during conflict

No Comments

No Known Activations