INDEX

Explanations

references to people, especially those with notable contributions or associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

zy

-0.16

":""

-0.15

YY

-0.15

edy

-0.15

GLE

-0.15

YLE

-0.15

uyá»ģn

-0.15

 GOODMAN

-0.15

 Goodman

-0.15

uye

-0.15

POSITIVE LOGITS

li

0.38

enna

0.28

lie

0.27

iov

0.27

hi

0.26

ial

0.25

lier

0.25

io

0.24

iard

0.24

uida

0.24

Activations Density 0.012%

references to people, especially those with notable contributions or associations

No Comments

No Known Activations