INDEX

Explanations

references to data and documentation 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 @ 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

doesn

-0.19

£

-0.15

ghi

-0.15

ãĥ¬ãĥ¼

-0.14

Caf

-0.14

Ð°ÑĢÑı

-0.14

abay

-0.13

skyt

-0.13

.lift

-0.13

 hasn

-0.13

POSITIVE LOGITS

0.26

am

0.25

Are

0.24

 Want

0.24

Die

0.23

ai

0.23

Do

0.23

 Have

0.22

ARE

0.20

 shalt

0.20

Activations Density 0.009%

references to data and documentation in various contexts

No Comments

No Known Activations