INDEX

Explanations

phrases related to performance and achievement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ikip

-0.16

 Ø§Ø®ØªÙĦ

-0.16

uars

-0.16

Zum

-0.14

uty

-0.14

Sortable

-0.14

chunks

-0.14

inel

-0.14

ONUS

-0.14

UpdatedAt

-0.13

POSITIVE LOGITS

 quite

0.29

 incredible

0.26

 impressive

0.25

 remarkable

0.25

 surprising

0.24

 amazing

0.23

 extraordinary

0.22

 impress

0.22

 unusual

0.21

quite

0.21

Activations Density 0.031%

phrases related to performance and achievement

No Comments

No Known Activations