INDEX

Explanations

references to meetings, reports, and evaluations regarding various events or implementations

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

 SayÄ±

-0.16

coni

-0.15

enstein

-0.15

 Ð¼Ð½Ð¾Ð³Ð¸Ñħ

-0.15

 Saunders

-0.15

 many

-0.14

astes

-0.14

_BEGIN

-0.14

 sorter

-0.14

 czÄĻ

-0.14

POSITIVE LOGITS

åĪĨåĪ«

0.24

 respectively

0.20

ãĢģä¸Ģ

0.17

 ê°ģê°ģ

0.17

 each

0.17

-one

0.16

atat

0.16

uito

0.16

ãģĿãĤĮ

0.16

-three

0.16

Activations Density 0.210%

references to meetings, reports, and evaluations regarding various events or implementations

No Comments

No Known Activations