INDEX

Explanations

references to "blueprint" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.15

zi

-0.15

ologue

-0.15

fel

-0.14

 Majority

-0.14

arking

-0.14

-redux

-0.14

æ´²

-0.14

ynn

-0.14

hangi

-0.14

POSITIVE LOGITS

æĽ¸é¤¨

0.17

laus

0.15

itti

0.15

teri

0.14

uche

0.14

·æĸ°

0.14

 Tears

0.14

uron

0.14

oes

0.14

late

0.13

Activations Density 0.003%

references to "blueprint" in various contexts

No Comments

No Known Activations