INDEX

Explanations

references to the concept of "free" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.18

la

-0.17

tra

-0.17

elastic

-0.17

re

-0.16

so

-0.16

à¸£

-0.16

ry

-0.15

st

-0.15

revision

-0.15

POSITIVE LOGITS

bie

0.27

bies

0.27

bsd

0.19

esktop

0.17

 à¹Ĩ

0.16

-floating

0.16

hold

0.16

zeitig

0.16

 dÃłng

0.15

-ÑĤÐ°ÐºÐ¸

0.15

Activations Density 0.050%

references to the concept of "free" in various contexts

No Comments

No Known Activations