INDEX

Explanations

bitwise operations and flags commonly used in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Rodgers

-0.16

acades

-0.15

za

-0.15

ZA

-0.14

getTable

-0.14

 Rogers

-0.14

 guts

-0.13

labs

-0.13

ruz

-0.13

ilton

-0.13

POSITIVE LOGITS

endi

0.16

orn

0.15

itsu

0.15

è¾

0.14

 Commons

0.14

istrovstvÃŃ

0.14

Compat

0.14

omb

0.14

.asc

0.14

awi

0.14

Activations Density 0.033%

bitwise operations and flags commonly used in programming

No Comments

No Known Activations