INDEX

Explanations

references to enrollment, economic conditions, and financial metrics in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

yled

-0.16

edin

-0.14

ÅĤÄħ

-0.14

alia

-0.13

arias

-0.13

Î½Î¿Î½

-0.13

uary

-0.13

ìĶ©

-0.13

kÃ¼

-0.13

pecified

-0.12

POSITIVE LOGITS

 accompanies

0.19

due

0.18

 since

0.18

ä¼´

0.17

 fortunes

0.17

 accompany

0.16

per

0.16

 accompanied

0.16

_since

0.15

 accompanying

0.15

Activations Density 0.118%

references to enrollment, economic conditions, and financial metrics in various contexts

No Comments

No Known Activations