INDEX

Explanations

numerical measurements related to dimensions and sizes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 âĹĦ

-0.17

 Maul

-0.16

 Mage

-0.15

INLINE

-0.15

 McCl

-0.15

 Mang

-0.15

 METH

-0.15

 Morgan

-0.15

 Meth

-0.15

Miz

-0.15

POSITIVE LOGITS

mm

0.70

mm

0.70

MM

0.53

-mm

0.53

MM

0.52

 Ð¼Ð¼

0.52

 mill

0.51

_mm

0.50

.mm

0.47

(mm

0.44

Activations Density 0.040%

numerical measurements related to dimensions and sizes

No Comments

No Known Activations