INDEX

Explanations

technical terms and code-related content within data processing and spatial 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

adge

-0.16

lesc

-0.14

avanaugh

-0.14

.osgi

-0.13

noinspection

-0.13

erialization

-0.13

.IsSuccess

-0.13

ATUS

-0.13

],&

-0.13

OKIE

-0.13

POSITIVE LOGITS

<-

0.35

<-

0.30

%>

0.26

=NULL

0.25

[[

0.25

\$

0.21

(TRUE

0.21

<<-

0.21

.df

0.20

NA

0.20

Activations Density 0.039%

technical terms and code-related content within data processing and spatial analysis contexts

No Comments

No Known Activations