INDEX

Explanations

references to organizations, establishments, or their respective properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

arger

-0.14

ift

-0.14

ensis

-0.13

 nhau

-0.13

venues

-0.13

Cr

-0.13

igkeit

-0.13

arg

-0.13

↵

-0.13

cr

-0.13

POSITIVE LOGITS

 itself

0.26

wide

0.21

's

0.20

åıĬåħ¶

0.20

-wide

0.18

’s

0.18

.scalablytyped

0.16

uale

0.15

aviest

0.15

AdapterManager

0.14

Activations Density 0.559%

references to organizations, establishments, or their respective properties

No Comments

No Known Activations