INDEX

Explanations

size measurements 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

inf

-0.15

ahlen

-0.14

Ĥæķ°

-0.14

loud

-0.14

immers

-0.14

 Cunningham

-0.14

Ð¾Ð²ÐµÑĢ

-0.14

sis

-0.14

IPA

-0.14

POSITIVE LOGITS

 equivalent

0.32

 size

0.25

 Equivalent

0.25

 equivalents

0.24

Equivalent

0.24

-size

0.23

-sized

0.23

size

0.23

 sizeof

0.22

 tamaÃ±o

0.21

Activations Density 0.123%

size measurements in various contexts

No Comments

No Known Activations