INDEX

Explanations

phrases associated with processing and handling data in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

IPC

-0.16

reten

-0.14

ÐµÐº

-0.14

 GiÃ¡o

-0.14

Ð»Ð°Ð²Ð°

-0.14

.vertx

-0.14

bench

-0.14

 Ð¿Ð¾Ð³

-0.14

ikel

-0.13

stadt

-0.13

POSITIVE LOGITS

 plugs

0.20

 plug

0.20

 Plug

0.19

 Maya

0.19

CustomAttributes

0.18

 matte

0.17

Plug

0.17

rious

0.16

plug

0.16

 cmds

0.15

Activations Density 0.004%

phrases associated with processing and handling data in programming contexts

No Comments

No Known Activations