INDEX

Explanations

instructions and descriptions related to grooming and cleaning tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

STACK

-0.17

BuilderFactory

-0.17

ÙĪÙĤ

-0.16

ady

-0.14

IDGE

-0.14

Republic

-0.14

adx

-0.14

 Tout

-0.13

UFF

-0.13

áºŃc

-0.13

POSITIVE LOGITS

 tool

0.31

 tools

0.30

tools

0.28

 spat

0.27

å·¥åħ·

0.27

 brushes

0.26

 brush

0.26

 wand

0.25

-tools

0.25

tool

0.24

Activations Density 0.205%

instructions and descriptions related to grooming and cleaning tasks

No Comments

No Known Activations