INDEX

Explanations

actions related to cleaning and organizing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Ø¬Ø¯Ø§

-0.16

umbo

-0.15

rov

-0.14

pon

-0.14

adm

-0.13

PO

-0.13

 Coleman

-0.13

.axis

-0.13

arrow

-0.13

à¸¹à¹Ī

-0.13

POSITIVE LOGITS

 cleared

0.24

 clearing

0.24

 clears

0.20

 doubt

0.19

 away

0.18

 clearance

0.18

 Clearance

0.17

-clear

0.17

 debris

0.17

 Clears

0.17

Activations Density 0.043%

actions related to cleaning and organizing

No Comments

No Known Activations