INDEX

Explanations

references to mathematical equations and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Cent

-0.15

ahlen

-0.14

wdx

-0.14

PFN

-0.14

OE

-0.13

RenderingContext

-0.13

vd

-0.13

rez

-0.13

ughs

-0.13

[[[

-0.13

POSITIVE LOGITS

umb

0.16

abbr

0.16

.reporting

0.15

vÃŃ

0.15

 resp

0.14

OTH

0.14

åĽº

0.14

aris

0.14

ifen

0.14

oth

0.13

Activations Density 0.450%

references to mathematical equations and notation

No Comments

No Known Activations