INDEX

Explanations

numerical identifiers and references commonly associated with academic or research citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

atel

-0.18

ÐµÑĢÐ¾

-0.17

cntl

-0.15

icens

-0.15

ero

-0.15

eru

-0.15

 Giang

-0.15

illions

-0.15

anka

-0.14

 Macro

-0.14

POSITIVE LOGITS

omit

0.20

çľģ

0.16

vale

0.15

creens

0.15

 Stard

0.15

 Pell

0.14

 Lesson

0.14

ogh

0.14

ows

0.14

_SYM

0.14

Activations Density 0.029%

numerical identifiers and references commonly associated with academic or research citations

No Comments

No Known Activations