INDEX

Explanations

references to technical implementation issues and web development terms

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

_MT

-0.16

(;;

-0.15

 laten

-0.14

 Morrow

-0.14

 BOOST

-0.14

 èĪ

-0.14

abox

-0.14

iard

-0.14

idot

-0.14

Ngb

-0.13

POSITIVE LOGITS

Ext

0.23

 xtype

0.23

Cls

0.18

sen

0.17

 Nebraska

0.16

.qq

0.16

proxy

0.16

sen

0.15

Sen

0.15

Xt

0.15

Activations Density 0.044%

references to technical implementation issues and web development terms

No Comments

No Known Activations