INDEX

Explanations

actions related to cleaning and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

TK

-0.15

_cpus

-0.14

 lá»ĩ

-0.14

adla

-0.14

iale

-0.14

ifestyles

-0.14

_OS

-0.14

 Ð¾ÑģÐ²ÐµÑī

-0.13

lap

-0.13

aight

-0.13

POSITIVE LOGITS

 thoroughly

0.34

 surfaces

0.25

 thorough

0.21

 mess

0.20

 accumulated

0.20

 spills

0.18

 fingerprints

0.18

 Mess

0.17

 floors

0.17

 Grimm

0.17

Activations Density 0.081%

actions related to cleaning and organization

No Comments

No Known Activations