INDEX

Explanations

specific impactful or negative descriptors related to situations or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ysi

-0.16

 Reich

-0.14

ãĥ£

-0.14

 vess

-0.14

ãĥ³ãĥĸ

-0.14

otes

-0.14

fifo

-0.14

fik

-0.13

Î³ÏīÎ³

-0.13

 Karlov

-0.13

POSITIVE LOGITS

 part

0.29

 portions

0.28

 portion

0.28

 parts

0.26

éĥ¨åĪĨ

0.24

 parte

0.23

 Portions

0.21

 Parts

0.20

 czÄĻ

0.20

 ÄįÃ¡sti

0.20

Activations Density 0.006%

specific impactful or negative descriptors related to situations or actions

No Comments

No Known Activations