INDEX

Explanations

references to Integrated Circuits (IC) and their related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

agnar

-0.17

acht

-0.16

hurst

-0.15

 Sokol

-0.14

avy

-0.14

Ð¾Ð¼ÐµÐ½

-0.14

ught

-0.14

insula

-0.14

 afterwards

-0.14

 Bernardino

-0.14

POSITIVE LOGITS

 Stam

0.17

ATAB

0.16

æħİ

0.14

 Rosenberg

0.14

ITA

0.14

rames

0.14

 Daniels

0.14

BAT

0.14

erne

0.14

 dÃ¡ng

0.14

Activations Density 0.008%

references to Integrated Circuits (IC) and their related terminology

No Comments

No Known Activations