INDEX

Explanations

references to organizational structures and rules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

.scalablytyped

-0.18

nett

-0.15

agne

-0.14

 ÙģØ§Ø±Ø³

-0.14

ldr

-0.14

 Frid

-0.14

 Cros

-0.14

ÃŃch

-0.14

ixer

-0.14

eten

-0.13

POSITIVE LOGITS

jew

0.41

 jewelry

0.40

 diamond

0.38

 jewellery

0.37

 Jewelry

0.36

 diamonds

0.36

Jew

0.35

diamond

0.32

 jewel

0.32

 Diamonds

0.31

Activations Density 0.049%

references to organizational structures and rules

No Comments

No Known Activations