INDEX

Explanations

phrases related to vigilance or attentiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ynes

-0.18

 Marr

-0.16

uai

-0.15

uais

-0.14

_reserved

-0.14

ersistence

-0.14

jez

-0.14

ÑĥÐ½Ðº

-0.14

/nginx

-0.13

urat

-0.13

POSITIVE LOGITS

 watch

0.31

 lookout

0.29

.watch

0.25

out

0.25

Watch

0.24

-watch

0.23

 Watch

0.23

 peeled

0.23

 watches

0.23

watch

0.22

Activations Density 0.031%

phrases related to vigilance or attentiveness

No Comments

No Known Activations