INDEX

Explanations

terms associated with partnerships and collaborative projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

prec

-0.17

 prÃ©c

-0.16

è©

-0.16

fa

-0.15

 prec

-0.15

 Prec

-0.14

 unified

-0.14

 almost

-0.14

 quite

-0.13

POSITIVE LOGITS

unker

0.15

herits

0.15

contents

0.14

 Guarantee

0.14

Circular

0.14

olleyError

0.13

Ĥæķ°

0.13

å²Ĺ

0.13

.todos

0.13

utenberg

0.13

Activations Density 0.251%

terms associated with partnerships and collaborative projects

No Comments

No Known Activations