INDEX

Explanations

words and phrases related to changes and trends in professional and technical environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

rio

-0.15

uche

-0.15

ãĥĥãĥĹ

-0.14

ongyang

-0.14

ijo

-0.13

loc

-0.13

il

-0.13

à¸§à¸¥

-0.13

ids

-0.13

 transforms

-0.13

POSITIVE LOGITS

 broad

0.46

 broader

0.37

Broad

0.36

 widest

0.36

 broaden

0.35

å¹¿

0.35

 wide

0.35

 Broad

0.34

 breadth

0.34

 rá»Ļng

0.34

Activations Density 0.362%

words and phrases related to changes and trends in professional and technical environments

No Comments

No Known Activations