INDEX

Explanations

phrases that indicate small quantities or numbers

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

imals

-0.15

ignal

-0.15

ÑĤÐ°

-0.14

uel

-0.14

ç·Ĵ

-0.14

«

-0.13

Ð¶ÐµÐ½ÑĮ

-0.13

uell

-0.13

anon

-0.13

UEL

-0.13

POSITIVE LOGITS

ynn

0.16

ŀĭ

0.16

 dozen

0.16

 Ø¹Ø²

0.15

ÎºÎ·

0.15

enaire

0.14

lotte

0.14

YTE

0.14

ãĥ¼ãĥ³

0.14

idelity

0.14

Activations Density 0.061%

phrases that indicate small quantities or numbers

No Comments

No Known Activations