INDEX

Explanations

references to Creative Commons licenses

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

errer

-0.15

uelle

-0.14

HW

-0.14

hid

-0.14

EGIN

-0.14

UREMENT

-0.14

ALLEL

-0.14

á¿ĸ

-0.14

hr

-0.14

rog

-0.14

POSITIVE LOGITS

BY

0.23

lesi

0.19

eler

0.18

rane

0.17

pill

0.16

ording

0.15

Zam

0.15

/licenses

0.15

-by

0.15

asionally

0.15

Activations Density 0.010%

references to Creative Commons licenses

No Comments

No Known Activations