INDEX

Explanations

phrases that convey a sense of contradiction or complexity in relationships

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

Ð¾Ð²Ð¾

-0.16

yre

-0.15

precated

-0.15

Ð¾Ð²

-0.15

ë¡Ŀ

-0.14

arsers

-0.14

utral

-0.14

iros

-0.14

utherland

-0.14

MaxY

-0.14

POSITIVE LOGITS

ny

0.16

que

0.15

Pey

0.15

agma

0.15

ahn

0.15

choice

0.14

ington

0.14

 Moff

0.14

Î³ÏĮ

0.14

Activations Density 0.417%

phrases that convey a sense of contradiction or complexity in relationships

No Comments

No Known Activations