INDEX

Explanations

patterns of repetition and redundancy in activities and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

kiye

-0.15

 overall

-0.15

ere

-0.14

 periodic

-0.14

arest

-0.14

iÃ³

-0.14

 Twice

-0.14

 span

-0.14

lÃ¼

-0.14

uen

-0.14

POSITIVE LOGITS

ad

0.35

Repeat

0.23

again

0.22

 repeat

0.22

 Repeat

0.21

repeat

0.21

-repeat

0.20

until

0.20

 Ð¿Ð¾Ð²ÑĤÐ¾ÑĢ

0.20

à¸§à¸Ļ

0.19

Activations Density 0.139%

patterns of repetition and redundancy in activities and processes

No Comments

No Known Activations