INDEX

Explanations

concepts related to communication and control in systems, particularly emphasizing consent and expectation

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

 cannabin

-0.17

iew

-0.16

ron

-0.13

Ø§Ø±Ø´

-0.13

Î

-0.13

 funk

-0.13

 CreateTable

-0.13

ronics

-0.13

 Bernardino

-0.13

æĴ®

-0.13

POSITIVE LOGITS

car

0.20

 tooth

0.19

 football

0.17

 airplane

0.17

 movie

0.16

 automobile

0.16

 cars

0.15

edd

0.15

 airline

0.15

 baseball

0.15

Activations Density 0.670%

concepts related to communication and control in systems, particularly emphasizing consent and expectation

No Comments

No Known Activations