INDEX

Explanations

references to relational dynamics or connections between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ickle

-0.15

ä¹Ī

-0.15

andan

-0.15

aldi

-0.15

Interop

-0.14

elo

-0.14

uar

-0.14

viz

-0.14

ually

-0.13

one

-0.13

POSITIVE LOGITS

/am

0.27

 sexes

0.23

âĢĮØ§ÙĦÙħÙĦÙĦÛĮ

0.20

two

0.20

zeit

0.18

/about

0.17

 ÑģÐ¾Ð±Ð¾Ð¹

0.17

 genders

0.16

Ordinal

0.16

 them

0.15

Activations Density 0.055%

references to relational dynamics or connections between entities

No Comments

No Known Activations