INDEX

Explanations

structured data fields or attributes in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

fty

-0.16

ushima

-0.15

jie

-0.15

pliers

-0.14

raman

-0.14

Ã©rt

-0.13

alyze

-0.13

ignon

-0.13

errer

-0.12

iversal

-0.12

POSITIVE LOGITS

.scalablytyped

0.13

æķ¦

0.12

 Giles

0.12

otos

0.12

 cooperating

0.12

-LAST

0.12

 ÐºÐ¾Ð¶Ð½Ð¾Ð³Ð¾

0.11

CommandEvent

0.11

unde

0.11

.UnitTesting

0.11

Activations Density 0.523%

structured data fields or attributes in a programming context

No Comments

No Known Activations