INDEX

Explanations

terms related to sliding or movement, particularly in a technological or graphical context

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

mie

-0.20

tesy

-0.18

drawing

-0.16

pid

-0.16

land

-0.16

ilde

-0.15

pler

-0.15

lier

-0.15

ILT

-0.15

mos

-0.15

POSITIVE LOGITS

/sl

0.22

.slide

0.21

hare

0.20

 Slide

0.17

-slide

0.17

 slide

0.17

kest

0.16

/slider

0.16

Äįan

0.15

Activations Density 0.015%

terms related to sliding or movement, particularly in a technological or graphical context

No Comments

No Known Activations