INDEX

Explanations

architectural details and features related to buildings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 fondo

-0.15

orsch

-0.14

chyb

-0.14

chor

-0.14

 Walls

-0.14

Marks

-0.14

RING

-0.14

skyt

-0.14

camp

-0.14

ocale

-0.14

POSITIVE LOGITS

 window

0.23

 windows

0.23

 Window

0.19

-window

0.17

kus

0.17

 front

0.17

window

0.17

/window

0.17

 panels

0.17

 porch

0.16

Activations Density 0.050%

architectural details and features related to buildings

No Comments

No Known Activations