INDEX

Explanations

references to residents and their experiences or status within a community

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ù

-0.17

zes

-0.16

iom

-0.16

vincia

-0.15

resse

-0.15

nowledge

-0.15

 nhau

-0.15

icolor

-0.15

asma

-0.14

erk

-0.14

POSITIVE LOGITS

ials

0.21

ally

0.19

rics

0.17

stvo

0.16

elijke

0.15

ric

0.15

ãģ¡ãģ¯

0.15

elijk

0.14

hip

0.14

Activations Density 0.033%

references to residents and their experiences or status within a community

No Comments

No Known Activations