INDEX

Explanations

terms related to solubility and chemical properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oyal

-0.15

arian

-0.14

 Source

-0.14

Nit

-0.14

 source

-0.14

_closure

-0.13

 steady

-0.13

 prote

-0.13

 lumin

-0.13

 distant

-0.13

POSITIVE LOGITS

sol

0.23

 solvent

0.21

.sol

0.20

 polarity

0.18

 misc

0.18

 Misc

0.18

 Banc

0.17

 polar

0.17

Partition

0.16

misc

0.16

Activations Density 0.062%

terms related to solubility and chemical properties

No Comments

No Known Activations