INDEX

Explanations

references to historical topics and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

/he

-0.18

vÃŃ

-0.16

woo

-0.15

 Meng

-0.14

Ã©g

-0.13

uguay

-0.13

stri

-0.13

indir

-0.13

 solic

-0.13

 Melee

-0.13

POSITIVE LOGITS

ure

0.16

hower

0.15

OfDay

0.15

ures

0.14

iage

0.14

esk

0.14

vertis

0.14

ÚĨÙĩ

0.14

URES

0.14

/current

0.14

Activations Density 0.033%

references to historical topics and events

No Comments

No Known Activations