INDEX

Explanations

phrases that indicate a level of emphasis or importance in discussions or reviews

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

essim

-0.17

çĭ

-0.15

lauf

-0.15

ãĤ¿ãĥ¼

-0.15

ãĥ¼ãĥ

-0.15

Å¡t

-0.14

uslim

-0.14

utan

-0.14

FormsModule

-0.14

ocop

-0.14

POSITIVE LOGITS

 taste

0.15

cho

0.14

pl

0.14

ìĨĶ

0.14

 Wilkinson

0.13

 malignant

0.13

.onError

0.13

Activations Density 0.055%

phrases that indicate a level of emphasis or importance in discussions or reviews

No Comments

No Known Activations