INDEX

Explanations

mathematical and programming symbols associated with variables and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

-0.14

èĸ

-0.13

vents

-0.13

sph

-0.13

ØªÙģ

-0.13

 dele

-0.13

,false

-0.13

ouser

-0.13

 mostly

-0.13

POSITIVE LOGITS

0.38

0.34

=”

0.23

="

0.23

='

0.21

=↵

0.20

?=

0.19

 equals

0.19

ï¼Ŀ

0.19

=(

0.19

Activations Density 0.200%

mathematical and programming symbols associated with variables and functions

No Comments

No Known Activations

mathematical and programming symbols associated with variables and functions

No Comments

No Known Activations