INDEX

Explanations

phrases that emphasize any variety of situations or elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 quelques

-0.16

 Some

-0.16

ÙĬÙĩ

-0.15

 some

-0.15

ania

-0.15

ä¸ĢäºĽ

-0.15

reira

-0.14

ÐµÑı

-0.14

ped

-0.14

rej

-0.14

POSITIVE LOGITS

/all

0.33

ones

0.30

THING

0.30

place

0.28

 sort

0.25

 kind

0.24

one

0.23

thin

0.23

kind

0.22

ONE

0.22

Activations Density 0.099%

phrases that emphasize any variety of situations or elements

No Comments

No Known Activations