INDEX

Explanations

technical terms and concepts related to mathematical modeling and data structures

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

 Pleasant

-0.15

 axiom

-0.14

abb

-0.14

 konkrÃ©t

-0.13

 Rich

-0.13

Lint

-0.13

_submit

-0.13

formula

-0.13

—

-0.13

 bills

-0.13

POSITIVE LOGITS

(:,

0.19

 HACK

0.17

NaN

0.16

ÌĤ

0.15

.ravel

0.15

 array

0.15

ught

0.15

åŃĺäºİ

0.15

 Returned

0.14

 è¢

0.14

Activations Density 0.022%

technical terms and concepts related to mathematical modeling and data structures

No Comments

No Known Activations