INDEX

Explanations

phrases indicating where individuals reside or are based

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

orsi

-0.16

.Compile

-0.15

ä¸įäºĨ

-0.15

 erect

-0.14

 Properties

-0.14

folk

-0.14

arius

-0.13

.boot

-0.13

plat

-0.13

heck

-0.13

POSITIVE LOGITS

 NÄĽm

0.17

 subur

0.15

 prostitu

0.15

 Ð¾ÑģÐ½Ð¾Ð²Ñĸ

0.15

 Hayes

0.14

 rural

0.13

ãĤĩ

0.13

 Ð¼ÐµÑĤÐ¾Ñİ

0.13

 Cá»Ļng

0.13

QUENCY

0.13

Activations Density 0.081%

phrases indicating where individuals reside or are based

No Comments

No Known Activations