INDEX

Explanations

forms of the word "stand," indicating a focus on standing positions or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

mediate

-0.17

curacy

-0.17

atern

-0.17

pher

-0.16

zym

-0.16

urator

-0.16

uger

-0.15

Responder

-0.15

imen

-0.15

icans

-0.15

POSITIVE LOGITS

-alone

0.41

alone

0.35

still

0.31

 alone

0.26

pipes

0.25

arde

0.25

 Alone

0.25

pipe

0.24

ARDS

0.24

ings

0.24

Activations Density 0.010%

forms of the word "stand," indicating a focus on standing positions or actions

No Comments

No Known Activations