INDEX

Explanations

instances of numeric values and references to years

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

ARSER

-0.15

abe

-0.15

iken

-0.15

 ragaz

-0.14

-0.13

 ""},↵

-0.13

Intialized

-0.13

-CP

-0.12

ãĤ¤ãĥ³ãĥĪ

-0.12

tractor

-0.12

POSITIVE LOGITS

ä»¥åıĬ

0.24

ï¼Įä»¥åıĬ

0.24

 plus

0.20

 followed

0.20

 ê·¸ë¦¬ê³ł

0.20

 sowie

0.19

 samt

0.19

 oraz

0.19

 dÃ¡le

0.18

ãģĿãģĹãģ¦

0.17

Activations Density 0.185%

instances of numeric values and references to years

No Comments

No Known Activations