INDEX

Explanations

phrases that suggest problem-solving and the pursuit of solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãĥ¼ãĥĭ

-0.17

ernes

-0.16

ãĥ¼ãĤ¹ãĥĪ

-0.15

hydr

-0.15

ëĭ¥

-0.14

ãĥ³ãĥĨ

-0.14

ŀæĢ§

-0.14

uraa

-0.14

ÐµÑĢÑĮ

-0.14

 {{--<

-0.14

POSITIVE LOGITS

roker

0.17

 uten

0.15

 somehow

0.14

emoc

0.14

roid

0.14

 ways

0.14

 somew

0.13

ench

0.13

ç¨

0.13

arked

0.13

Activations Density 0.048%

phrases that suggest problem-solving and the pursuit of solutions

No Comments

No Known Activations