INDEX

Explanations

words and themes related to education and support for others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

thon

-0.16

rium

-0.15

inati

-0.15

ahren

-0.15

wort

-0.14

áºŃt

-0.14

layan

-0.14

Ã¼ÅŁ

-0.14

lue

-0.14

MLE

-0.14

POSITIVE LOGITS

 towards

0.28

 toward

0.26

 into

0.26

 accordingly

0.21

 onto

0.21

into

0.20

how

0.20

to

0.19

 away

0.18

/us

0.18

Activations Density 0.130%

words and themes related to education and support for others

No Comments

No Known Activations