INDEX

Explanations

references to complex theoretical concepts and advanced scientific discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 franc

-0.15

 Dalton

-0.15

obox

-0.14

Callbacks

-0.14

CELER

-0.14

å²Ĺ

-0.14

taj

-0.14

ixel

-0.14

 Fern

-0.14

jes

-0.14

POSITIVE LOGITS

 holog

0.26

 dual

0.25

 Dual

0.25

Dual

0.24

 Wilson

0.22

Ryu

0.20

Ad

0.20

Wilson

0.20

 gravity

0.19

gravity

0.18

Activations Density 0.039%

references to complex theoretical concepts and advanced scientific discussions

No Comments

No Known Activations