INDEX

Explanations

phrases indicating emotional responses or critiques towards films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ervo

-0.16

 thrilling

-0.15

 thrill

-0.15

 fascinated

-0.14

 hÆ°á»Łng

-0.14

-ignore

-0.14

rapper

-0.14

Thr

-0.14

 Consort

-0.14

åĺ

-0.14

POSITIVE LOGITS

 heart

0.30

 touching

0.30

 tear

0.29

heart

0.25

 warm

0.24

 sentimental

0.24

 tender

0.24

 sweet

0.23

 sensitive

0.23

touch

0.23

Activations Density 0.177%

phrases indicating emotional responses or critiques towards films

No Comments

No Known Activations