INDEX

Explanations

articles and determiners associated with people and objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 seins

-0.17

 Designer

-0.16

³

-0.15

è¯Ŀ

-0.15

 sufferers

-0.15

 lungs

-0.14

uckles

-0.14

 tits

-0.14

alog

-0.14

---</

-0.13

POSITIVE LOGITS

 group

0.24

 woman

0.23

 passer

0.23

 female

0.22

 crowd

0.22

 young

0.21

 elderly

0.20

van

0.20

 pregnant

0.19

 swarm

0.19

Activations Density 0.187%

articles and determiners associated with people and objects

No Comments

No Known Activations