INDEX

Explanations

references to processes, measurements, and functionalities related to technology and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

VML

-0.17

beits

-0.16

 ((__

-0.15

aklÄ±

-0.15

NEY

-0.14

ÐŁÐļ

-0.14

polator

-0.14

ventus

-0.14

 tails

-0.14

POSITIVE LOGITS

 done

0.33

 erfol

0.31

 occurs

0.30

 occurring

0.28

 happening

0.28

 occur

0.27

done

0.27

 performed

0.26

 Done

0.25

.done

0.25

Activations Density 0.442%

references to processes, measurements, and functionalities related to technology and systems

No Comments

No Known Activations