INDEX

Explanations

conjunctions and phrases that connect ideas or elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

chooser

-0.15

vester

-0.15

ìĽĲìĿ´

-0.14

Ð³Ð»

-0.14

 ØªÙĥ

-0.14

presence

-0.14

é¢Ħè§Ī

-0.14

 *)__

-0.14

idge

-0.13

.directive

-0.13

POSITIVE LOGITS

 alike

0.27

oria

0.17

asar

0.17

 respectively

0.15

fe

0.14

etc

0.14

es

0.13

Howard

0.13

ordo

0.13

 Ø§Ø´

0.13

Activations Density 0.252%

conjunctions and phrases that connect ideas or elements

No Comments

No Known Activations