INDEX

Explanations

mentions of "California."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÑģÑı

-0.17

linger

-0.17

laps

-0.16

.scalablytyped

-0.16

ÃĹ↵↵

-0.16

Calendar

-0.15

-calendar

-0.15

ches

-0.15

pile

-0.14

uong

-0.14

POSITIVE LOGITS

ifornia

0.28

iforn

0.25

 dreaming

0.21

 Dream

0.21

æ¹¾

0.19

aver

0.18

 rais

0.18

UTION

0.18

esium

0.18

 dream

0.17

Activations Density 0.018%

mentions of "California."

No Comments

No Known Activations