INDEX

Explanations

terms related to energy efficiency and operational improvements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

EXPORT

-0.15

 widest

-0.15

eur

-0.15

Gut

-0.14

Extras

-0.14

anch

-0.14

Fon

-0.14

çĥĪ

-0.14

 springfox

-0.13

extras

-0.13

POSITIVE LOGITS

 efficiency

0.59

 Efficiency

0.54

eff

0.52

-eff

0.51

 efficient

0.51

Eff

0.50

 efficiencies

0.49

eff

0.49

_eff

0.49

EFF

0.48

Activations Density 0.092%

terms related to energy efficiency and operational improvements

No Comments

No Known Activations