INDEX

Explanations

words and phrases related to hardness and flexibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 èµ¤

-0.19

veau

-0.15

 libc

-0.14

 íĴ

-0.14

akis

-0.14

iveness

-0.14

arov

-0.13

ABB

-0.13

Ì£

-0.13

amo

-0.13

POSITIVE LOGITS

-hard

0.27

 hard

0.27

 Hard

0.26

Hard

0.24

_hard

0.23

hard

0.22

 HARD

0.21

 hardness

0.19

 harder

0.19

zf

0.18

Activations Density 0.064%

words and phrases related to hardness and flexibility

No Comments

No Known Activations