INDEX

Explanations

references to permissions and licensing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ã¦r

-0.16

Ã¦

-0.14

utive

-0.14

sup

-0.14

ÙĤØ©

-0.14

Yup

-0.14

adders

-0.14

cur

-0.14

unks

-0.14

aida

-0.14

POSITIVE LOGITS

elerik

0.17

/Peak

0.17

ella

0.16

xEB

0.16

(Spring

0.15

aison

0.15

stants

0.15

 Peaks

0.14

buie

0.14

.MockMvc

0.14

Activations Density 0.003%

references to permissions and licensing information

No Comments

No Known Activations