INDEX

Explanations

groups of people characterized by their actions or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ä¸Ģä¸ªäºº

-0.20

 itself

-0.18

çļĦä¸Ģä¸ª

-0.17

 gangs

-0.16

.timedelta

-0.16

ols

-0.15

urrencies

-0.14

urre

-0.14

Vac

-0.14

 Ø§ÙĦØ°ÙĬ

-0.14

POSITIVE LOGITS

 themselves

0.38

 members

0.21

 ones

0.19

 yourselves

0.18

 mere

0.18

 thems

0.18

äºĽ

0.18

are

0.17

 part

0.17

 ÑģÐ°Ð¼Ð¸

0.17

Activations Density 0.335%

groups of people characterized by their actions or attributes

No Comments

No Known Activations