INDEX

Explanations

phrases and terms that describe hierarchical relationships or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

luv

-0.17

apore

-0.15

heit

-0.15

umpt

-0.15

erken

-0.15

KIT

-0.15

agara

-0.14

riÃ¨re

-0.14

riere

-0.14

bach

-0.14

POSITIVE LOGITS

 view

0.26

 contact

0.22

 departure

0.22

 entry

0.21

 sale

0.20

view

0.20

 Ð·ÑĢÐµÐ½Ð¸Ñı

0.20

 vista

0.19

 Entry

0.19

 View

0.19

Activations Density 0.017%

phrases and terms that describe hierarchical relationships or classifications

No Comments

No Known Activations