INDEX

Explanations

terms related to engineering and custom component design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 moduleId

-0.17

.Module

-0.16

 MODULE

-0.16

 Maiden

-0.16

mist

-0.16

 Mentor

-0.15

Ã±

-0.15

module

-0.15

 Mint

-0.15

 Module

-0.15

POSITIVE LOGITS

Mur

1.35

mur

1.33

Mur

1.30

 Murphy

1.19

mur

1.13

 mouse

0.82

 Murder

0.81

 Murdoch

0.79

 murder

0.77

 murm

0.76

Activations Density 0.026%

terms related to engineering and custom component design

No Comments

No Known Activations