INDEX

Explanations

tabular data and structured information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

serter

-0.14

è³¢

-0.14

PIE

-0.14

ettel

-0.14

èĲ½ãģ¡

-0.14

 susp

-0.13

Å¡el

-0.13

 portions

-0.13

éĻĦ

-0.13

 Portions

-0.13

POSITIVE LOGITS

ua

0.15

bek

0.15

ver

0.14

vit

0.14

Ð¾Ð»Ñı

0.14

 Newman

0.13

 getC

0.13

 ÑĩÐ¸Ñģ

0.13

TypeDef

0.13

 Succ

0.13

Activations Density 0.059%

tabular data and structured information

No Comments

No Known Activations