INDEX

Explanations

words indicating obligation or requirement

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

 respectively

-0.17

ISTA

-0.15

 each

-0.15

istÃ©

-0.15

 nhau

-0.14

ersive

-0.14

cona

-0.14

celik

-0.14

idden

-0.13

ãĥĬãĥ¼

-0.13

POSITIVE LOGITS

 together

0.30

 Together

0.26

 combination

0.24

ä¸Ģèµ·

0.23

 zusammen

0.22

Together

0.22

combination

0.22

gether

0.22

 combined

0.21

 Ð²Ð¼ÐµÑģÑĤÐµ

0.21

Activations Density 0.004%

words indicating obligation or requirement

No Comments

No Known Activations