INDEX

Explanations

instances of the word "wake" and variations related to awakening or rising

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

inho

-0.16

sons

-0.16

idal

-0.15

ADS

-0.15

Ø§Ø³Ø±

-0.14

undles

-0.14

iano

-0.14

acle

-0.14

ucci

-0.14

reno

-0.14

POSITIVE LOGITS

-up

0.26

up

0.24

fulness

0.23

wake

0.23

-Up

0.22

Wake

0.21

 Wake

0.21

 wake

0.20

yr

0.18

up

0.17

Activations Density 0.008%

instances of the word "wake" and variations related to awakening or rising

No Comments

No Known Activations