INDEX

Explanations

phrases related to instructional or operational guidance for devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

zych

-0.18

HeaderCode

-0.16

ï»¿#

-0.15

.updateDynamic

-0.15

pone

-0.15

Äįel

-0.15

AGMA

-0.15

tuk

-0.15

.RightToLeft

-0.14

blr

-0.14

POSITIVE LOGITS

 press

0.82

 Press

0.75

press

0.71

 pressing

0.70

 presses

0.69

Press

0.68

 pressed

0.66

 PRESS

0.58

_press

0.57

PRESS

0.52

Activations Density 0.239%

phrases related to instructional or operational guidance for devices

No Comments

No Known Activations