INDEX

Explanations

keywords and phrases related to generating and sharing ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

urm

-0.19

chez

-0.18

oyo

-0.17

umper

-0.17

æĬ¼

-0.16

abbo

-0.15

AdapterFactory

-0.15

arest

-0.15

zew

-0.15

é§ħå¾ĴæŃ©

-0.14

POSITIVE LOGITS

 ways

0.18

erals

0.16

0.15

Tri

0.15

 Ways

0.15

 Ã¶t

0.15

ocos

0.14

ycz

0.14

Activations Density 0.051%

keywords and phrases related to generating and sharing ideas

No Comments

No Known Activations