INDEX

Explanations

phrases related to retention rates and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

umer

-0.15

thur

-0.14

¦æĥħ

-0.14

ansom

-0.14

ãĥªãĤ«

-0.14

ÐµÐ²Ð¸

-0.14

¯¼

-0.14

adia

-0.14

-0.13

ç¿°

-0.13

POSITIVE LOGITS

0.20

),

0.19

 than

0.18

 anymore

0.17

than

0.17

nor

0.17

Nor

0.17

0.15

 âĢ¢

0.14

Activations Density 4.938%

phrases related to retention rates and statistics

No Comments

No Known Activations