INDEX

Explanations

instances of the word "hang" and its variations, indicating a focus on activities or states related to hanging or being suspended

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

.appspot

-0.17

PRINTF

-0.15

ahead

-0.14

gnu

-0.14

 Ð²Ð¿ÐµÑĢÐµÐ´

-0.14

.codes

-0.14

sson

-0.14

Ã²ng

-0.14

 Ahead

-0.14

 ahead

-0.13

POSITIVE LOGITS

 hung

0.28

 hang

0.27

 hanging

0.25

 Hang

0.25

 hangs

0.24

Hang

0.24

 Hanging

0.23

hang

0.20

over

0.19

 suspended

0.18

Activations Density 0.028%

instances of the word "hang" and its variations, indicating a focus on activities or states related to hanging or being suspended

No Comments

No Known Activations