INDEX

Explanations

information pertaining to complex systems and processes, particularly within literature and analysis contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

aina

-0.17

|required

-0.16

ipse

-0.15

etto

-0.14

omer

-0.14

yyn

-0.14

-reply

-0.14

ÑģÑĤÑĢÐ¸

-0.14

stra

-0.13

LOPT

-0.13

POSITIVE LOGITS

 include

0.27

:↵

0.21

 includes

0.20

 ÅŁun

0.20

 examples

0.19

include

0.18

 Examples

0.18

 Include

0.18

 Ø¹Ø¨Ø§Ø±Øª

0.17

å¦Ĥä¸ĭ

0.17

Activations Density 0.254%

information pertaining to complex systems and processes, particularly within literature and analysis contexts

No Comments

No Known Activations