INDEX

Explanations

concepts related to performance and quality 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

and

-0.18

 Ã©s

-0.16

ãĤĦ

-0.16

 bÃ¥de

-0.16

æĪĸèĢħ

-0.15

and

-0.15

 Ð¸

-0.15

 vÃł

-0.15

æĹ¢

-0.14

 totiÅ¾

-0.14

POSITIVE LOGITS

 alike

0.35

/or

0.22

 importantly

0.20

quot

0.15

 respectively

0.15

 serta

0.15

atrice

0.14

/OR

0.14

ãĤ·ãĤ¢

0.14

ÑĶÐ¼

0.14

Activations Density 0.656%

concepts related to performance and quality in various contexts

No Comments

No Known Activations