INDEX

Explanations

inquiries related to understanding behaviors and social dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

kin

-0.18

erland

-0.17

AYER

-0.15

pll

-0.15

ILLISE

-0.14

Çİ

-0.14

ama

-0.14

Fav

-0.14

 Heights

-0.14

åĲ§

-0.14

POSITIVE LOGITS

 à¤ĩà¤¤à¤¨

0.25

 seemingly

0.23

so

0.22

 tÃ£o

0.22

 suddenly

0.20

 despite

0.19

 láº¡i

0.18

why

0.17

why

0.17

 seem

0.17

Activations Density 0.131%

inquiries related to understanding behaviors and social dynamics

No Comments

No Known Activations