INDEX

Explanations

phrases and words related to physical boundaries or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ð±Ð¾

-0.15

 ÙĪØ±Ø²

-0.14

Ð¸ÑĢÐ¾Ð²

-0.14

maxlength

-0.14

angular

-0.14

heimer

-0.14

ibble

-0.14

asio

-0.14

WARDED

-0.14

ì§Ģë¥¼

-0.13

POSITIVE LOGITS

pin

0.39

pins

0.32

pin

0.32

 pins

0.29

 pinned

0.28

lie

0.27

-pin

0.26

Pin

0.26

Pin

0.26

SCORE

0.25

Activations Density 0.018%

phrases and words related to physical boundaries or limitations

No Comments

No Known Activations